burden locally, so only the network output (the
classification itself) needs to be transmitted over
LongFi (Figure
A
).
LongHive Sensor Suite
In our review of relevant literature and existing
commercial solutions, we found a slew of passive
sensors that have proven to give some indication
of hive health. First and foremost, we want to
provide beekeepers with real-time data that they
will use to augment their existing heuristics and
improve productivity.
• Variation inhive weightis a sign of honey
production and population.
• Temperatureis a simple but critical source
of information; bees like to keep very
precise thermal conditions for optimal hive
development. In fact, they have fascinating
mechanisms for maintaining this delicate
homeostasis:when the hive is too hot, they
fan their wings to increase convective cooling;
when it’s too cool, they generate heat by
vibrating their flight muscles.
• Similarly, beekeepers must keep an eye on the
relativehumidityin their hive — eggs cannot
hatch when it’s too dry, but damp conditions
can be a sign of mold or disease.
• Carbon dioxideis released into the hive as
a byproduct of honey production. Thus, a
lack of proper ventilation can result inCO
2
poisoningand other maladies. Beekeepers
maintain this balance by making tweaks to
airflow and insulation.
• The acoustic signalsemitted by a hive can be
a rich source of information, but it will take a
more complex processing pipeline to make
sense of it (more on this in a moment).
ANTONIO SCALA is
studying computer science
and mathematics at Villanova
University. After graduation, he
plans to enter the space industry.
NATHAN PIRHALLA has
a degree in finance from the
University of Pittsburgh. He is also
passionate about local farming
and making unobtrusive hardware.
EVAN DIEWALD is working on
his PhD in mechanical engineering
at Carnegie Mellon. He loves to find
new applications for deep learning
and additive manufacturing.
TIME REQUIRED:
8–10 Hours
DIFFICULTY:
Moderate. Familiarity with Raspberry Pi
and deep learning recommended, but not
necessary.
COST:
$150
MATERIALS
» Raspberry Pi 3B single-board computer
» Seeed ReSpeaker 2-Mics Pi HAT
» Load cells, 50kg (4) SparkFun Electronics
SEN-10245
» Load cell amplifier SparkFun HX711
» Air Quality breakout board SparkFun CCS811
» Temperature sensor, DS18B20 type
» STM32L0 LoRa/Sigfox Discovery Kit
STMicroelectronics B-L072Z-LRWAN1
» Wood screws
» 2×4 board, roughly 8' length
» Plywood sheets, ¼"×18"×22"
TOOLS
» 3D printer
» Power drill
» Table saw
Nathan Pirhalla, Adobe Stock - diyanadimitrova
Raspberry Pi
LoRaWAN
microcontroller
Grafana
dashboard
Helium
console
Postgres
DB
Microphone
HAT
DL classification Decoded payloadCayenneLPP-encoded
payload
Acoustic signals CO
2
, temperature,
humidity, hive weight
Real-time, transient,
multi-sensor datastream
Environmental
sensors
65
A
makeprojects.com
M75_064-7_LongHive_F2.indd 65M75_064-7_LongHive_F2.indd 65 10/12/20 11:59 AM10/12/20 11:59 AM
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.