New tech approaches to understanding hive health - Video and Data Analytics

Beekeeping & Apiculture Forum

Help Support Beekeeping & Apiculture Forum:

This site may earn a commission from merchant affiliate links, including eBay, Amazon, and others.

KTemby

New Bee
Joined
Nov 20, 2015
Messages
17
Reaction score
0
Location
Santa Barbara
Hive Type
Langstroth
Number of Hives
7
Well this is a bit disheartening - my last post, and the replies to it, was deleted - beekeepingforum.co.uk/showthread.php?p=510960

Apologies if sharing new ideas and our project has offended anyone. I reached out to Pete the Moderator and haven't heard anything back on the post removal, so maybe there was a glitch. This seemed like the most appropriate place of anywhere to discuss ideas, beekeeping software and technology, but I'm new to the forum so I apologies in advance if this is out of place. Ok here goes again -

Hoping to create a conversation around technology and beekeeping. I grew up with bees, am a hobbyist beekeeper and work in a medical robotics company by day. For the last year my team and I have been working on a tech to bring healthcare analytics to bee hives, in a project we're calling EyesOnHives.

We designed the original system for a local beekeeping guru to have an easier time helping other beekeepers with their bees. He simply didn't have time to be driving all over town helping new beekeepers deal with their issues, and was asking myself and others to manually count how many bees came out of hives to get some idea on hive strength, and whether there were problematic areas around town with declines affecting multiple hives. We got inspired by the concept, and showed that tech could make the whole process a lot easier!

Our approach is a weatherproof device that uses a camera and computer to visually monitor what goes on at the bee hive entrance all day. Activity is measured by tracking the number of bees flying in front using onboard computerised image processing. Video and data is viewable remotely through an analytics platform, where other hives' data are available to see too.

Beekeepers in our 15 hive beta program used EyesOnHives to monitor and take action to manage colonies suffering from queen failure, ants attacks (yes, that's a thing) and robbing. The ants were a real surprise for us - they really can and do take down even a strong hive when they want to (we're in a drought here, which has exacerbated things). Having the early warning through video has enabled us to provide a safety net for other beeks, who can see videos of other hives, and alert each other to things like ants attacking.

We wanted to hear what the community had to say about our approach to non-invasively monitor hive activity. As far as we know we're the first to achieve this at scale, and have seen some pretty interesting behavior patterns. Happy to show actual data.

Please let me know if you have any interest in hearing more, or questions.
 
Last edited:
Well this is a bit disheartening - my last post, and the replies to it, was deleted - beekeepingforum.co.uk/showthread.php?p=510960

Apologies if sharing new ideas and our project has offended anyone. I reached out to Pete the Moderator and haven't heard anything back on the post removal, so maybe there was a glitch.

I have not deleted your post, perhaps Admin did, nor have you tried to contact me...well not on this forum or via e mail... maybe you tried to phone me and i missed the call, but you could of left a message on the answer machine you know.

I suspect this will be getting deleted again.
 
I find your novel approach to bee hive colony fascinating.
Where I live often as not any radio signal is impossible... what about a recording device data could be downloaded to on an apiary visit?
Tells us more.. links etc etc
Keep it coming!

Yeghes da
 
I have not deleted your post, perhaps Admin did, nor have you tried to contact me...well not on this forum or via e mail... maybe you tried to phone me and i missed the call, but you could of left a message on the answer machine you know.

Hi Pete, thanks for your reply - I used the "Contact Us" forum tool to submit feedback - I had assumed it went to you, but perhaps it went to the Admin account. Thanks for letting me know.

I suspect this will be getting deleted again.
Can you please share why?
 
Last edited:
Hi icanhopit! Thanks for your interest.

Looks like I can't embed links to screenshots of data till I hit 10 posts. There's a great one that shows how we detected a queenless hive, intervened and watched it recover, all through the activity metric.

We have a lot of people with flaky internet connections near their hives too. Our approach so far has been to store up to 2 weeks of video samples, and the data onboard.

Would you actually be interested in seeing data after the fact, rather than in real time?
 
Can you please share why?

I can only guess at the moment that Admin viewed it as some form of commercial advertising, and that is not allowed on the forum, or any links to own commercial websites.
 
Thanks again Pete. Our project is designed by beekeepers, for beekeepers, and we want to talk with other beekeepers about it!!

We're hoping to create a mid to long form discussion to better understand what people are interested in, and we want to continue to improve the system to make more beekeepers happy, and able to study and help their bees! We're engaged locally, but are trying to better understand people's interest at a broader level.
 
Last edited:
Yes we do. We presently have 15 systems supporting our local community of beekeepers, and I help run our local association. The system is making it easier to better understand the state of bees in our local community, and we want to expand the project.

We're aiming to identify patterns that show all kinds of interesting hive states and the data scientists on the team believe it can be done with enough hives creating enough data. This is part of why we're passionate about people using the EyesOnHives platform. We're working every day to make the server and apps more usable and effective for people too, and continually pushing software improvements to the fielded devices.

We want to see if other beekeepers, clubs and communities are interested in this.

It's not just data in the app, but the easy communication framework built around the data that helps too. For example, you can click on a video that you think shows something interesting and alert me or another beekeeper, and I'll not just get a notification, I'll be able to see exactly what you're looking at through video too. I used this just this morning to let a local beta user know that their hive was covered in ants.
 
It's a project we have been running in our local beekeeping community in Santa Barbara California for the past year. Right now there are 15 hives monitored. There is a campaign to expand the program to 45 systems, we realize it's not for everyone, but if people are interested in the project we're happy to talk about it. AMA.
 
Last edited:
Would not want to have the responsibility of kicking another Flow's Hive fiasco into life... but the tech behind all these novel beekeepering devices is of interest and possibly transferable to the real world !

Yeghes da
 
but the tech behind all these novel beekeepering devices is of interest and possibly transferable to the real world !

Yeghes da

Thanks for your encouragement icanhopit! Here's a picture that represented the turning point for me on whether the tech had real value - I didn't see it myself, but the data pretty clearly showed a drop in activity, that turned out to be a failed queen. A simple intervention of an extra couple of frames of brood from the adjacent hive, allowed the bees to raise an emergency queen, and I even got a honey harvest from it. Amazing creatures!

OyJGtNW.png
 
What other scenarios do you have? e.g. wasp attacks, weather conditions and swarming. For me it is not suitable as I do not have a home apiary, only out apiaries.
 
Hi Anduril,

Thanks for your question. Certainly the biggest surprise was detecting the orientation activity - it actually has a signal we can pick out using analytics.

jsMtDiS.jpg


Here's one where we saw a different pattern - robbing - in the daily data.

zSP52GO.png


Our goal presently is to build up the dataset and analytics to identify more behaviors in the data, and use beekeeping expertise to sanity check the videos and confirm the data makes sense.
 
This is very interesting to me as I've currently plugged a few sensors into my hive. Are you developing your own model to analysis the data or did you start with some published research?

What I've found is that location even a few miles apart has an impact on the hive performance, I'm toying with seeing if I can pull down some local weather data to use as some form of weighting.

Mine is just playing, not an ongoing endeavour like you appear to be doing.

Good luck.
 
What exactly are you measuring? The number of bees entering & leaving the hive? How do you measure colony health in winter when the bees are probably at their most vulnerable, and when they're not flying?

Like Domino, I have some sensors measuring temperature & humidity but it's just for fun. I also have a bunch of other sensors I plan on building into the kit over winter so I should have more next year. Unfortunately they're not as well located as they could be, so they're not giving accurate brood temperatures: http://beespi.mybluemix.net/, although my camera merely watches them - no sophisticated algorithms (yet).
 
.
I can see that this system gives a new tool to researchers to find out, how colony reacts to different things, like to bee foraging behaviour.

I am sure that when ordinary beekeepers start to reseach things, a huge soup is ready, and it produces more wrong information than right.

It needs quite a big planning, what you are going to reviele out, and then check, that the phenomenom can be measured and picked out from colony's life.

Balance hive teaches many things about foraging, and this traffic counting may reviele out new things and how strong are the effects.
.
 
Back
Top