Backyard Brains Logo

Neuroscience for Everyone!

+1 (855) GET-SPIKES (855-438-7745)
items ()
Menu

The Fellows Summer Experience: Tigers Game and July Fourth Parade

2018-Jul-09 Filed under: Fellowship,Lifestyle Comments Off

One of the most attractive things about a BYB Summer Fellowship is the chance to spend a summer in colorful Ann Arbor. We changed the program name from an internship to a fellowship because of the lasting connections made throughout the summer, and these connections are made possible by the things we all do together! Before we get to some project updates, here’s a little bit about our summer together so far.

Take Me Out To The Ball Game

Last summer, we sponsored a student whose visa required participation in a “cultural appreciation” event, so we piled into a bus and headed over to Comerica Park for some of America’s favorite sport, baseball. It was such a hit, we went again this year! Luckily, Backyard Brains signature color  (orange!) matches pretty well with the Tigers brand 😉

Fourth of July Parade

Another celebrated BYB Summer Fellowship pastime is the Jaycee’s Fourth of July Parade! Each year, the fellows design and build a costume representing their summer research and wear it as BYB walks in the annual parade! Check out some of the looks from this year:

 
 
 
   

Meet the Fellows, See the Projects

Catch up with our Fellows! Since our Fellowship started, each fellow has been hard at work on their summer research. Check out these posts introducing each Fellowship research track:

First Progress Reports:

If you’ve been dying for an update on what we’ve been researching, fret no more! Feast your eyes on our first batch of updates!

Second Progress Reports:

Science marches ever onward! The Fellows have kept plugging away on their research in between all the fun and games, and here are their newest updates!

Conclusions:

The summer is winding down, and with it our Fellowship. While scientific exploration is never really finished, here are some wrap-ups from our Fellows on the projects they have devoted their inquiry to over the past weeks.

Tags:

Human, Quiet, Crow: Teaching Computers to Distinguish Birdsong

2018-Jun-25 Filed under: Fellowship,Hardware Comments Off

Hey guys, it’s Yifan again. There has been a lot of progress since my first blog post. As promised last time, I was able to finish a functional prototype with all the legacies left for me. I put the device in the woods to get recording for the first time. The results, to my pleasant surprise, are very impressive. The device recorded 12 hours of data and wrote it to the SD card.

 

(Device in the field)

(Device field location)

 

 

 

 

 

 

 

 

 

 

 

 

The quality of the microphone is quite decent, and although it cannot record birds from far away, it can record the bird on the same tree very clearly. Here are some of my hand-selected bird song clips from the 12 hour recording. Enjoy the sound of nature! 

Birdsong recording

If you did listen to the recordings, hopefully you can tell that one of the recordings is not a bird song (it’s a train whistle). Differentiating between bird calls and noises is a easy task for use human, but it can be a challenge to a computer. Then why do we need to use programs to help us identify these sounds? Take a look at this recording image.

The entire recording is 12 hours, if I choose to hand select out all the bird songs, it can take hours. If we want our device to continuously record for a week, we humans simply do not have the patience to go through hundreds of hours of data. Computers, on the other hand, love analyzing long recordings, and they can be trained to do it very well.

Luckily, pyAudioAnalysis, the library our team uses for classifying different bird species, also has the functionality to segment a long recording based on a mathematical model called Hidden Markov Model (HMM). In the near future, I will hopefully be able to use this method to segment all the recordings from our device.

The process of utilizing HMM model including these following steps. First, you need to generate annotation files for known recordings as training data. The annotation looks like this:

The model is trained by these given class names. After the model is trained, we can then use it to classify an unfamiliar recording. Based on similarities, the model generates marks for segmentation.

In the most recent test run, I trained the model using one single file, and tested the model’s accuracy on a very simple recording. Here is a graph representing the segmentation results.

 

         

Looks like it’s working, right? Well not really. Although this particular segmentation is pretty accurate, others are not very satisfactory. However, I did only use one training input, which can definitely be improved. Another possible improvement I can think of is to train the model with only two classes: bird and not bird. Since we’ll still have to use the classifier to differentiate different kinds of birds, the segmentation model only needs to be able to tell the difference between birds and non-birds. We will see how that goes. Wish me luck!

 

Tags:

Tech Trek and Fellow Updates

2018-Jun-22 Filed under: Fellowship,Outreach Comments Off

Fresh, organic, locally sourced meditation researchLast Friday, Backyard Brains once again opened our doors (even wider–they’re always open during business hours!) to our fellow and aspiring citizen scientists as a part of this year’s Ann Arbor Tech Trek!  Dozens of local tech companies had their doors open to the public that evening and we, like our friends around town, had people streaming in from open to close! BYB has participated for the last few years, and it is always a hit.

For four hours on Friday afternoon, we were packed with people from all walks of life who were interested in learning about Backyard Brains and neuroscience! It was a day of education, outreach, and new connections. In the office, we demonstrated our classic, the Human to Human Interface, as well as The Claw, and we even helped people control Mario with their eye blinks!

Our Summer Fellows also got in on the action, presenting their work down in the Makerspace at All Hands Active. This was the first chance our fellows got to share their science with the community, letting people in on their secrets and experiment rigs. For example, Silkmoth Fellow Jess was running experiments on a cockroach antenna during Tech Trek: Some kids were watching when she used different odors to try to get a reaction in the antenna, as pictured below:

It was definitely a unique opportunity, full of its own trials. According to Mantis Shrimp Fellow Dan, “I was trying to collect behavioral data with the mantis shrimp while his implants were falling out, and people would come by who obligingly ooh-ed and ahh-ed at the prep and politely listened to my spiel about EMGs and the strike. I’ve never presented about my research while actively conducting it.”

Meet the Fellows, See the Projects

Catch up with our Fellows! Since our Fellowship started, each fellow has been hard at work on their summer research. Saw a cool project and you want to know more? Check out these posts introducing each Fellowship research track:

First Progress Reports:

If you’ve been dying for an update on what we’ve been researching, fret no more! Feast your eyes on our first batch of updates!

Second Progress Reports:

Science marches ever onward! The Fellows have kept plugging away on their research in between all the fun and games, and here are their newest updates!

Conclusions:

The summer is winding down, and with it our Fellowship. While scientific exploration is never really finished, here are some wrap-ups from our Fellows on the projects they have devoted their inquiry to over the past weeks.

Tags:
« Newer Posts — Older Posts »

Search

Categories

Archives

Administrative