FAQ

Errors

Cant get SMS.
We know of some users having issues in Lebanon and in the US with some network providers. Please send a screenshot of entering your phone number and also name of your provider to support@beescanning.com.

 

Inside the app

Why is there a silhouette bee when I want to add an image?
Move your camera to sync it with the size of the bees and your picture will be optimal for analyse. About 20-25 cm distance gives good quality for analysing.

Where in the hive should I take the pictures?
Take pictures from 2-3 brood frames to cover 3000 -6000 bees.

How should I take the picture?
a. Please, dont try to cover the frame side with just one picture!
b. Place the comb so you can hold the phone with both hands. Less shaky.
c. We now prefer sunlight in 90 degrees, not side light since it creates shadows and contrasts.
d. Take the picture from about 20-25 cm from the frame, in right angel. USE THE REFERENCE BEE. Unsharp, too close or far away images will impair results.
e. On a Modified Dadant (448×286 mm) frame, and 3/4 Langstroth (448x 232 mm) take 4 portrait images on each side. On a Shallow Langstroth (448×137 mm) or 3/4 (448x 159 mm) take 2 landscape images from each side.
f. Avoid overlapping.


Please click HERE to see as how to NOT take images.

 

What is a collection?
A collection contains the images you take from a hive or even an apiary. Results from analysing will reflect the average of the collection.

Can images be stored in different collections and sent for analyse later?
Yes, take images and build collections offline, press analyse when you are ready and connected.

How do I create new collections to analyse?
Tap the hives name. Standing in the hive. Tap + button in bottom bar, “New analyse”

Can you edit metadata, like apiary, hive etc?
Yes you can edit names anytime. A tip may be to prepare creating apiaries and hives before starting the work. Then its easy to just select the specific hive when needed.

Is there a way to search images, collections?
Standing in apiary or hive view, tap sort.

How do I delete an image or a collection?
Press three dots, choose delete.

How many images is maximum in a collection?
Maximum 30.

How many images should I take from one colony?
Depending on infestation level you will want to picture between 3000 -6000 bees. With 250 bees in each image that is 12 – 24 images, covering 2 – 4 brood frames. It is often enough with 12 images if there is normal coverage of bees on the frames.

Why not take pictures from frames above the excluder?
Mites are preferably found on the brood and results tend to vary more the further away you get.

When should I take the pictures?
Preferably in the beginning of the season and just after your main honeyflow, 1-2 months before wintering. Before and after supers are on hives.

Can I access my images and results?
Yes they can be accessed within the app or from http://tagger.beescanning.com

Can I change language?
Default is the same language as in your phone. That is if we have translated to your language otherwise default is english. Ready translations in 2.0 are Chinese, Czech, Dutch, English, Finnish, French, German, Italian, Japanese, Lithuanian, Norwegian, Spanish and Swedish. Polish is coming soon. We welcome any help translating to additional languages.  For now faq is in English and Swedish only.

How to zoom?
To validate result pinch with two fingers.

About the app

What cellphone is needed?
On android 7.0 and on iOS 8.0

Where can I download the app?
Available on Appstore and Google Play

What is the price of using the app?
Free to download and analyse varroa. A subscription model charging for power functions is planned.

Is the app depending on internet connection?
You can capture images offline and send for analyse when you have connection. Analysing is done on our servers not on the client.

What time does it take to collect a collection?
As long as it takes to lift 2-3 frames out of the brood chamber. About 5 minutes.


How long does it take to get results?
Depending on number of images and your connection it usually takes less than a minute. Once images are uploaded analysing goes in milliseconds.

What is varroa infestation?
Varroa infestation is the number of mites on the bees divided by the number of bees. In a sample with 3 mites on 300 bees that would equal 3/300 = 0,01 = 1%. So that is the number of phoretic mites, (mites on bees, not in the brood) detected in the images in relation to the number of bees. The detected infestation level in the images is then multiplied with a factor. We are constantly evaluating what factor we use. The factor reflects the ratio between observable and actual number of varroa mites on adult bees as measured with alcohol washing. (The factor may be subject to change as our research progress.) The resulting figure is then divided with the number of bees in the images analysed. Example: 3 mites are detected. 3*factor 8 (here  arbitrary value) =  24 mites calculated. 24 mites per 2500 bees in images = 24/2500 = 0,0096 ≈ 1% infestation.

What is Deformed Wing Virus, DWV?
Varroa transfers viruses when it ingests on its prey. Presence of DWV is a strong indicator of high infestation level, though absence is not a reliable sign varroa is not at hand. Thus you may want to check closer when DWV is detected. The analysing accuracy is not yet very reliable but will improve soon.

Is the app reliable?
On launch we only know that in our environment, the software finds the Varroa, (the DWV-bees and the Queen are found but not displayed for now) with great accuracy. The more images we can collect from you using the app the better it will become. The neural network will learn from its errors and improve. Look at it as you are part of a great pioneering mission. In the first versions prepare for missteps and report them, helping our common progress. Disclaimer: Results are based on our field studies and may depend on our location, methods of manual analyses, breed of bees, etc. Please read more in https://beescanning.com/eng/studie/  We have conducted fieldstudies since 2016 collecting images comparing to results from alco washing from the same frames images were taken. If you wish to calibrate the image analysing results with your own study washing samples with alcohol we would appreciate your feedback and incorporate any new knowledge that may be due to your circumstances. Have in mind that any result of low infestation is not a guarantee you don’t need to treat. Depending on your individual conditions; as what type of bees, time in season, reinvasion from neighbors, quality and the number of images at hand it may influence the interpretation of the result. On the other hand if a high infestation is recorded that is of course a strong signal to be taken seriously.

How can results bee used?
Results will indicate if you may need to treat the colony. Results may soon even be used to find trends and colonies with varroa resistance treats.

0% Great! You may want to confirm this result by collecting more images and/or examine with alcohol washing. The colony may be of interest for breeding resistance.

<0,5% Depending on time of season this may be ok. Note the colony for further evaluation.

1% Plan for treatment, monitor closely.

2% Warning, monitor closely. Plan for treatment and queen change.

3% You will want to act soon! This is a threshold!

5% There is danger! This colony is in jeopardy and may be a source of reinvasion in your neighborhood. Act immediately.

How should I treat the colony?
There are many options. Depending on time of season and your ways with bees you will have to choose your preferred method. Please read more at http://scientificbeekeeping.com/varroa-management/treatments-for-varroa/

When it comes to pesticide selection, one can reason as follows

In the spring / early summer, it is hardly advisable to use such agents where the risk of producing residues in honey is greater than just minimal. Then you can’t suggest Apistan (Tau-fluvallinate), Apivar (Amitraz), Bayvarol (Flumithrin), Checkmite (Coumaphose) USA. The active ingredients of such substances are fat-soluble and stored in wax. Therefore, these should be avoided at all. But if they are used, the Council should mark the frames between which strips are hung with these means. When these are circulated out of the bee community, the wax in these cakes is not recycled but burned, to avoid strain on the common wax pool in the country.

Thymol preparations are good to use in spring / early summer as thymol treatment with the right amount only slightly affects the breeding. Residual amounts of small amounts of thymol are not dangerous for anyone involved, on the contrary. Thymol is not built up in ever-increasing quantities in wax. TYmol normally requires two applications of some thymol pads. The second ten days after the first. After another 10 days, these are removed. In hot weather (30-35 °) half the amount is given every five days, ie 4 times.
Oxalic acid treatment in the form of evaporation (sublimation) can be used in the spring when bees can tolerate more than one treatment better than oxalic acid drop of sugar solution. Maybe oxalic acid drip goes better than late autumn / winter more than once. Since there are juveniles in the bee community, which it does in the spring, about 3 times treatment is required at one week intervals to cover a breeding period. Oxalic acid treatment requires good protective measures for the beekeeper.

Both of these treatments can also be used in the middle of summer if needed. Only a minority of communities will need it. You are then happy to wait for the harvest of honey until a week has passed between the end of the fight and the harvest to avoid too high amounts of honey. However, remember that it is more important to save communities than to save a small amount of honey from some harmless extra molecules.
So-called short-term treatment with formic acid usually occurs only once. Such treatment should be effective just as with oxalic acid 3 times at one week intervals. Myrysra inhibits breeding more than oxalic acid with such treatment.

In late summer / autumn treatment, thymol can be used as above, Apistan, Apivar, Bayvarol, Checkmite (USA), or oxalic acid evaporation 3 times.
You can wait with oxalic acid treatment if you choose this, unless the degree of infestation of varroa is very high, until late autumn / winter when the community is breeding free with oxalic acid drop 1 day.

Thymol and organic acids (oxalic and formic acid) are approved for use in organic beekeeping.
(Erik Österlund)

Where are analysed images stored?
Images are stored on our servers and/or in the cloud.

Who owns the images?
You. We own the rights to use them according to your agreement in Terms of Service. Even after should you choose to delete your images.

What happens if I loose my phone?
Your images may be recovered from the server. And will show up once you log in to your account.

What does the app icon symbolize?
It signals a vibrant technology that may help our bees. It also radiates the stress bees show from the small crabish parasites. As well as internet communication. The dynamic hexagons signals bees, the red dot varroa and danger, wifi stripes signals communication.

What is the accuracy of the image detection of varroa?
In our environment the so called recall is about 80%. That means the software finds 8 out of 10 varroa that are optically visble. We consider that enough for practical purposes, warning the beekeeper in time. The NN can find the mite even if only parts of it are visible or if its under a wing but results may be affected due to optical circumstances. We will keep learning how to integrate uncertain detections of difficult objects. Analysing video sequences will add to the accuracy and our knowledge on how the parasite and the host coexist.

What is the accuracy of image analysing counting bees?
In our environment the software performance is about +/- 5 %. That is how accurate the NN reports compared to the known test data. Counting is done by a totally different technology compared with the mite detection. We are rather certain the performance will improve fast.

What is the accuracy of detecting the Queen?
In our environment the software performance is better than +/- 5 %, it is actually a bit better. Detecting the queen is a much easier task than the varroa. Previous models of NN were good finding the queen but made many mistakes depicting especially long bees falsly. We therefore turned this feature on hold but will take it up once performance has improved.

Can the app find the Queen instantly?
We are planning to enable offline capabilities in updates.

What is the accuracy of DWV detection?
In our environment the software performance is not yet reliable +- 20% but improving. We are adding it now and would be grateful for more images with DWV to train the neural network. The NN seems to falsely identify some new born bees with DWV. Thats understandable because the NN seems to connect features of young bees with DWV. Older bees seldom show DWV since damaged ones normally are quickly eliminated.

The app falsely reports bee as queen and/or bee_with_varroa.

False positives will decrease as the AI learns from your reports and from our ongoing supervised training.

GDPR?
Please mail any question to support@beescanning.com

Why do you collect GPS information?
It is optional. You will have to agree on installing the app.We will use that for finding areas in the world where bees are healthy and to correlate this with other metadata as race etc.. in the search for resistance. It may also be used to warn you if there is an outbreak of disease in your region.

Quit the app?
On iPhones with homebutton double click it and swipe up to quit the app. On X swipe up and to the right. Press gently on app icon and on minus sign on each app to quit it.

The app is stalling/crasching?
Please report. Your images will be safe and retrieved from server when you log in again.

 

The poll “In next version”

  1. DWV
    Deformed wings is a strong indication the colony is in trouble. If a colony cant clean out dwv-bees there is great danger and it needs your immediate attention.
  2. Queen:
    The app is rather accurate in spotting the queen but can sometimes mistake a long bee for a queen. False positive may be easily detected though.
  3. Brood disorders:
    Warnings when abnormal cells are detected. AI is trained on sack- and chalk brood as well as european- american foul brood. Since some cliniquel symptoms are very alike and only can be established by laboratory examination, reporting of results will be limited to give warnings suggesting closer inspection and sampling. Eventually warnings will be handed on an urgency scale.
  4. Queen cell:
    Queen cells in different phases and of different quality may be of great importance for proper manegement.
  5. Number of bees in image:
    Currently not shown.
  6. Colony strength:
    Information about frame size, number of frames per box, number of boxes together with number of bees in the images can be used to calculate colony strength.
  7. Statistics:
    Comparing results from different times can be used to calculate how the colony copes with mites.
  8. Management :
    Tools for notes, queen, treatments, crop etc..
  9. Uncertain varroa?:
    Display found varroa where AI asses probability below 80%.

 

Project

How does the neural network learn?
The neural network, NN, is actively taught by a deep learning professional who has access to a good amount of training data. In short, an image of a varroa infested bee is shown to the neural network and we let the network guess. If the network guesses wrong, we let it know. It will then adjust itself very slightly to make a more educated guess next time. By doing this several thousand times the neural network will learn very abstract features and eventually become better than a human at visually detecting mites. However this is a very simplified way of looking at it. In reality, an artificial neural network is a very complex beast that is difficult to tame and comes in many different forms and shapes. One of the first milestones for the development team was to find the way of training that is optimal for this particular task. Finding very small objects in a huge amount of information. This is far more difficult than comparing images to a library of know objects.

What if you don’t find enough training images for the neural network?
A crowdsourcing campaign secured resources to develop Tagger. Our tool to structure images and manually label regions to train the NN. We have today collected about 35 000 images and will continue to use the data gathered from the app as a tool for further ongoing training of the neural network.

Is the development team actually capable of solving this task?
Since late 2018 we collaborate with Neurolearn AB a spinoff from Örebro University AI research. BeeScanning has attracted cutting edge developers in all fields necessary; in AI as well as in cloud- and system architecture.

Why hasn’t this been done before?
The required hardware and software wasn’t actually enough developed 2016 and the idea was probably too far-fetched to be taken seriously. The innovator Björn Lagerman has a long record of combining knowledge in new and creative ways as well as the experience to lead complex projects.

Where can I upload images?
Images are automatically uploaded to our site Tagger. You can also upload manually on http://tagger.beescanning.com and contribute by labeling and review regions.

How is the project financed?
Initially we were funded by backers on Kickstarter. We then received financing from the European Innovation Program, EIP and Vinnova. We are also supported by Almi Örebro and Handelsbanken in Lindesberg. Please read more at http://fribi.se/sponsorer/

Why have you received so many awards?
We are very happy to have been granted 15 awards. We like to think it is a combination of a growing awareness on the importance of bees and there problems as well as an unusual mix of hightech and lowtech.

https://beescanning.com/awards/