PosterPDF Available

A smart Internet of Things (loT) device for monitoring mosquito trap counts in the field while drinking coffee at your desk.

Authors:
  • Biogents AG, Regensburg, Germany
  • Biogents

Abstract

The BG-Counter is an autonomous new smart mosquito trap station that automatically differentiates mosquitoes from other insects, counts them, and wirelessly transmits results to a cloud server. Based on the industry-standard BG Sentinel, the BG-Counter enables real-time alerting as well as prediction models and historical analysis of infested areas. Vector control professionals can now establish surveillance programs with unprecedented data density, accuracy and real-time responsiveness, overcoming labor constraints associated with manual inspection. The BG-Counter can also sample local environmental data such as temperature, humidity, light, precipitation, or wind. Other sensor modules in the trap station’s periphery supply additional data; for example, wireless standing water sensors provide ”wet” or ”dry” status of nearby larval sites. As a result, both presence of adult mosquitoes and formation of breeding sites can be detected earlier and with greater precision, enabling faster, more targeted, and thus more effective, mosquito control. Since time-resolved mosquito abundance data are now routinely available, adulticiding can be performed when mosquitoes are the most active; also, the effectiveness of control measures can be validated immediately. The system is supported by a web-based database for storage of mosquito counts, geospatial and environmental data, and is automatically updated by the BG-Counters in the field. The data can be accessed, displayed and analyzed by the end user in a cloud-based “Management Central”, and also exported to Excel at the push of a button. The intuitive graphical user interface can be accessed from PCs as well as smartphones and tablets. This research was partly performed as part of the MCD project (www.mcdproject.org), which is funded by the European Union’s Framework 7 Health Innovation initiative (agreement number: 306105, project acronym: MCD).
The BG-Counter: A smart Internet of Things (IoT) device for monitoring mosquito trap counts
in the eld while drinking coee at your desk.
Martin Geier1, Michael Weber2, Andreas Rose1, Ulla Obermayr1, Charles Abadam3, Jay Kiser3, Catherine Pruszynski4, and Michael Doyle4
1 Biogents AG, Weissenburgstr. 22, 93055 Regensburg, Germany, martin.geier@biogents.com
2 onVector Technology, 825 La Crosse Ct, Sunnyvale, CA, michael@onvectortech.com
3 Suolk Mosquito Control, 866 Carolina Rd, Suolk, VA 23434
4 Florida Keys Mosquito Control District, 503 107th St. (Gulfside), Marathon, FL 33050
Features of the BG-Counter
The BG-Counter is an innovative and autonomous mosquito trap station that dierentiates mosquitoes from
other insects, counts them, and wirelessly transmits the results to a cloud server. Via the web application you
can manage and control the trap station from your desk.
This will provide new insights into daily activity patterns, adult density indices, population dynamics and
eectiveness of your mosquito control activities.
Vector control professionals can now establish surveillance programs with unprecedented data density and
accuracy, overcoming labor constraints associated with manual inspection. Also, the eectiveness of control
measures can be validated immediately.
The BG-Counter
reports mosquito counts remotely from everywhere in the world to an internet web page
samples local environmental data such as temperature, relative humidity, and optional wind speed,
rainfall, or water levels in potential breeding sites
lets you manage the trap and the application of attractants remotely
reduces costs associated with manually checking mosquito traps
TECHNOLOGY
Detection of mosquitoes
The patented insect sensor consists of arrays of infrared LEDs and light detectors that provide reliable and
sensitive detection and dierentiation of moquitoes from other objects entering the trap, see gure 1 and 2.
This technology was developed by onVector Technology in collaboration with Biogents.
Accuracy of correct mosquito counts under eld
conditions
To maximize the accuracy of the system the trap has to be rather selective for a broad range of mosquito
species. This is accomplished by the use of CO2 as an attractant and by the particular trap design. Mosquito
counts with an accuracy of 90% have been established in eld tests when working with CO2 as an attractant,
see table 1 and 2. The maximum counting frequency is about 5 mosquitoes per second. This means that up
to 18,000 mosquitoes can be counted per hour.
Web Service
The system is supported by a web-service including data communication and cloud storage of mosquito
counts, geospatial and environmental data.
The data can be accessed, displayed, analyzed, and downloaded as Excel les at the push of a button. The
intuitive graphical user interface can be accessed from PCs as well as smartphones and tablets.
The web application allows you to remotely switch the traps on and o in the eld. It also allows you to set
up varying time schedules to run the traps and set up application times of CO2.
The BG-Counter samples local environmental data such as temperature, humidity, and light. Other optional
sensor modules in the trap station’s periphery supply additional data: for example sensors for precipitation
and wind, or wireless standing water sensors provide „wet“ or „dry“ status of nearby larval sites. As a result,
both presence of adult mosquitoes and the formation of breeding sites can be detected earlier and with
greater precision, enabling faster and more targeted responses.
Technical Details
The heart of the BG-Counter is a highly integrated printed circuit board which incorporates:
an infrared sensor
environmental sensors for temperature, relative humidity and ambient light
a cellular module for communication with the web server
an SD card for onboard data storage, fan and C02 valve control
connections for optional peripheral devices such as attracting lights, rain sensors, wind sensors and stan-
ding water sensors
an optional network module to allow traps to wirelessly connect with remote devices and each other
two powerful microprocessors for control and communication
100
0
-100
-200
-300
-400
-500
200
300
400
500
Relative signal intensity
100
0
-100
-200
-300
-400
200
300
400
Relative signal intensity
-500
500
100
0
-100
-200
200
0 1 2 4 3 5 6 7 8 9 10 11 12
time in msec
Relative signal intensity
-300
-400
-500
300
400
500
Trap Information
Name Savannah Trap 1
Serial number 6
Location -16.900421, 145.739802
Active since 2015-03-24@11:40
CO2 Cylinder
85% (24 days)
500
400
300
200
100
0
00:00
00:30
01:00
01:30
02:00
02:30
03:00
03:30
04:00
04:30
05:00
05:30
06:00
06:30
07:00
07:30
08:00
08:30
09:00
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
22:00
22:30
23:00
23:30
00:00
Counter On: Fan On: CO2 On: Trap data sent:
18:00
Small objects: -
Mosquitoes: 74
Large objects: -
Trap location
Trap Schedule
Edit
Mon - Sun Fan
CO2
Counter
0:00 2:00 4:00 6:00 8:00 10:00 12:00 14:00 16:00 18:00 20:00 22:00 24:00
Filter
Filter by insect type Filter by time 2016-02-02 Range of y-Axis 0 - 500
Chart of Captures 2016-02-02 List of Captures <
<
Load Daily Charts
Developed by
TECHNOLOGY
Your traps
Biogents Trap 1
Biogents Trap2
Savannah Trap 1
Florida Keys Trap
Suffolk Trap
Dashboard
Prole
Logout
Traps
Savannah Trap 1
AMCA 82nd Annual Meeting, 2016, Savannah, Georgia, USA
Date Set Date collected Counted By Total
Mosquitoes % Accuracy
14/10/2015 15/10/2015 Human 120 100.00%
BG-Counter 120
21/10/2015 22/10/2015 Human 139 99.29%
BG-Counter 140
23/10/2015 24/10/2015 Human 171 98.84%
BG-Counter 173
27/10/2015 28/10/2015 Human 169 95.27%
BG-Counter 161
14/12/2015 15/12/2015 Human 183 77.22%
BG-Counter 237
15/12/2015 16/12/2015 Human 164 79.23%
BG-Counter 207
05/01/2016 06/01/2016 Human 5 35.71%*
BG-Counter 14
09/01/2016 10/01/2016 Human 38 82.61%
BG-Counter 46
13/01/2016 14/01/2016 Human 11 100,00%
BG-Counter 11
Figure 2: A mosquito that is sucked through the BG-Counter is detected by light detectors and generates a typical si-
gnal that can be dierentiated from the signals generated by larger or smaller insects.
BG-Counter station with BG-Sentinel 2 trap, CO2 source,
battery and rain shield. The station runs on solar power
(the solar panel is not displayed here).
Data are transferred to a web page that can be accessed
via PC, smartphone or tablet.
Large insects
like ies,
moths, ...
Mosquitoes
Small insects
like midges,
noseeuns,
fungus gnats, ...
Table 1: Field testing of the BG-Counter in the Florida Keys
The trap was programmed to release CO2 in half hour intervals.
Date Set Date Collected Counted By Mosquitoes % Accuracy
15/10/2015 16/10/2015 Human 136 95.59%
BG-Counter 130
20/10/2015 21/10/2015 Human 67 83.75%
BG-Counter 80
21/10/2015 22/10/2015 Human 197 94.42%
BG-Counter 186
22/10/2015 23/10/2015 Human 259 85.71%
BG-Counter 222
26/10/2015 27/10/2015 Human 55 83.64%
BG-Counter 46
27/10/2015 28/10/2015 Human 450 90.00%
BG-Counter 405
28/10/2015 29/10/2015 Human 404 94.80%
BG-Counter 383
29/10/2015 30/10/2015 Human 695 90.36%
BG-Counter 628
03/11/2015 04/11/2015 Human 238 86.97%
BG-Counter 207
04/11/2015 05/11/2015 Human 206 87.86%
BG-Counter 181
05/11/2015 06/11/2015 Human 199 90.95%
BG-Counter 181
09/11/2015 10/11/2015 Human 92 97.83%
BG-Counter 90
Table 2: Field testing of the BG-Counter in Suolk VA
The trap was programmed to release CO2 continuously.
* = heavy rain during sampling
Figure 1: An insect is sucked through the BG-Counter and disrupts the infrared ray. This is detected by the light detectors.
The signal from the light detectors depend on the size, shape, and wingbeat frequency of the insect.
Light de-
tectors
Infrared
LEDs
Figure 3: Example display of the user interface.
Infrared
light barrier
... , 카메 라 영상 이미지 분석 (Chen et al., 2012;Chiron et al., 2013Chiron et al., , 2014Tashakkori and Ghadiri, 2015;Tu et al., 2016;Magnier et al., 2018), 적외선 센서 (Kevan et al., 2009;Geier et al., 2016;Jiang et al., 2016;Pešović et al., 2017) (Souza et al., 2018). 최근, 벌통 입구 상단부 에 설치한 카메라로 영상을 녹화하여 SNR (Singal to Noise Ratio) 분석 (Tashakkori and Ghadiri, 2015), 배 경분리 (Background subtraction) 분석 (Tu et al., 2016), 3D 분석 (Chiron et al., 2013(Chiron et al., , 2014, 이미지 카운팅 소 프트웨어 (Magnier et al., 2018) (Kevan et al., 2009;Jiang et al., 2016;Pešović et al., 2017). ...
Article
Full-text available
Son J.D., Lim S., Kim D.I., Han G., Ilyasov R., Yunusbaev U., Kwon H.W. Automatic bee-counting system with dual infrared sensor based on ICT. Journal of Apiculture. 2019. 34(1) : 47-55. DOI: 10.17519/apiculture.2019.04.34.1.47. Abstract. Honey bees are a vital part of the food chain as the most important pollinators for a broad palette of crops and wild plants. The climate change and colony collapse disorder (CCD) phenomenon make it challenging to develop ICT solutions to predict changes in beehive and alert about potential threats. In this paper, we report the test results of the bee-counting system which stands out against the previous analogues due to its comprehensive components including an improved dual infrared sensor to detect honey bees entering and leaving the hive, environmental sensors that measure ambient and interior, a wireless network with the bluetooth low energy (BLE) to transmit the sensing data in real time to the gateway, and a cloud which accumulate and analyze data. To assess the system accuracy, 3 persons manually counted the outgoing and incoming honey bees using the video record of 360-minute length. The difference between automatic and manual measurements for outgoing and incoming scores were 3.98% and 4.43% respectively. These differences are relatively lower than previous analogues, which inspires a vision that the tested system is a good candidate to use in precise apicultural industry, scientific research and education.
Article
Effective mosquito surveillance and control relies on rapid and accurate identification of mosquito vectors and confounding sympatric species. As adoption of modified mosquito (MM) control techniques has increased, the value of monitoring the success of interventions has gained recognition and has pushed the field away from traditional ‘spray and pray’ approaches. Field evaluation and monitoring of MM control techniques that target specific species require massive volumes of surveillance data involving species-level identifications. However, traditional surveillance methods remain time and labor-intensive, requiring highly trained, experienced personnel. Health districts often lack the resources needed to collect essential data, and conventional entomological species identification involves a significant learning curve to produce consistent high accuracy data. These needs led us to develop MosID: a device that allows for high-accuracy mosquito species identification to enhance capability and capacity of mosquito surveillance programs. The device features high-resolution optics and enables batch image capture and species identification of mosquito specimens using computer vision. While development is ongoing, we share an update on key metrics of the MosID system. The identification algorithm, tested internally across 16 species, achieved 98.4 ± 0.6% % macro F1-score on a dataset of known species, unknown species used in training, and species reserved for testing (species, specimens respectively: 12, 1302; 12, 603; 7, 222). Preliminary user testing showed specimens were processed with MosID at a rate ranging from 181-600 specimens per hour. We also discuss other metrics within technical scope, such as mosquito sex and fluorescence detection, that may further support MM programs.
ResearchGate has not been able to resolve any references for this publication.