Hi! I’m Shreya and I just graduated from the Dwarkadas J. Sanghvi College of Engineering affiliated to the University of Mumbai in Electronics Engineering. During the last two years of my undergraduate study, I spent most of my vacations, free time and some weekends working as a research intern at the Indian Institute of Technology (IIT) Bombay where I completed several computer programming and embedded electronics projects. My undergraduate capstone project had me working with Artificial Neural Networks for ECG beat classification. This project was also completed at and funded by IIT Bombay.
Me on a train in India (during our final year class trip to Rishikesh)
Recently I have been really interested in neuroscience and EEGs, which is how I discovered Backyard Brains. I had been following their blog and Facebook posts for a few months, and that’s how I found out about this internship! I joined Backyard Brains on 12th June (got delayed because of final exams!) and I will be working on the Electric Fish project here for six months. This is my first time in the USA and so far, it’s been great! I’ve been enjoying the climate here – it’s a good change from the intense summer heat in Mumbai. I also love how Ann Arbor has so many different flower species!
Me and some beautiful flowers in Ann Arbor
Electric fish are a really interesting type of animal that can generate and detect electric fields around them to either stun prey or to communicate with other electric fish, detect objects and navigate. However, finding them and tracking them can be difficult, and many species have yet to be discovered! This project is aimed at building a device which can be deployed into the freshwater rivers of South America to detect and record the Electric Organ Discharges (EOD) of weakly electric fish as they swim past it. Each species has a unique EOD, which can be either wave-type or pulse-type. So, based on the nature of the recorded EOD, the species of the fish can be estimated and it can also be used to study the behaviour of the fish. This project is based on the research that Dr. Eric Fortune of the New Jersey Institute of Technology conducted in Ecuador. I will be using the Elephant Nose fish to test the device while prototyping.
Elephant Nose fish (source: Wikimedia Commons)
The Elephant Nose fish produces EODs which look like spikes when recorded using electrodes. So far, I have been able to amplify and see these spikes on an oscilloscope. I will be improving the filter and amplifier, using an Arduino to detect spikes in the recorded data, and saving this information along with time stamps on an SD card. Some of the challenges I will be facing while designing this are that the device needs to be waterproof and it should have power saving capabilities since it might have to run on batteries or solar energy for months at a time to be able to detect any electric fish.
Below are some of the spikes I recorded from the Elephant Nose fish as seen on an oscilloscope (along with 60 Hz noise).
I’m really enjoying working on this project here, at Backyard Brains, and I look forward to finishing this project!
BYB 2016 Fellows @ Tech Trek Last Year
This Friday 3pm – 7pm, Backyard Brains will be hosting an open house as part of this year’s A2 Tech Trek! This is a fun, annual event which coordinates open houses at dozens of local tech companies. This event showcases the vibrant tech company and startup community in Ann Arbor and is a chance for the public to see all the cool development going on in “hidden” office spaces around the city. You never know what kind of cool tech could be living in the office suites above a Ben and Jerry’s…
The event is free, but registration is required: Click Here to Register!
To help promote the event, BYB’s Greg Gage was recently featured on Live in the D, a local news program highlighting events in Southeastern Michigan. Greg Gage recorded Chuck Gaidica’s EMG signals and then, with the Human-To-Human Interface, helped Chuck control Bill Mayer of Ann Arbor SPARK, the organizer of the Tech Trek!
To see the video, follow this link:
See the Video!
We’ll be at our office, located at 308 1/2 State Street, all afternoon to give demonstrations and talk shop! Also, our summer research fellows will be down at All Hands Active, a community makerspace located downstairs at 255 E Liberty St. They are excited to talk with you about their projects! In case you missed any of them, here are the research projects! Your homework is to come prepared with a question for one of the fellows! There just might be a free sticker in it for you if you do…
For more information on the Tech Trek, check out:
From their website:
“Ann Arbor Tech Trek is a free community event and a terrific opportunity to see the real gems located inside the doors of many area tech companies. It’s also a chance to see what’s unique about downtown Ann Arbor.
Leading technology companies will open their doors to the public and showcase their latest innovations. Whether you’re a job seeker, student, professional, or someone curious about the Ann Arbor tech community, anyone is welcome to attend.
Each stop on the trek will create a fun, educational experience that reflects each company’s unique culture. Those on the tour will also enjoy refreshments, prizes, t-shirts, and giveaways.
Tech Trek is a win-win for companies, community, and a great way for the youth to explore possible career paths.”
We hope to see you Friday! Either at our office or at All Hands Active!
Hi, I’m Ilya Chugunov, a rising sophomore at UC Berkeley, majoring in Electrical Engineering and Computer Science. My hobbies include: hiking, archery, and pondering deeply about why my code doesn’t compile. As a member of the Backyard Brains fellowship this summer I will be studying the fascinating, and possibly unseen, behaviors of the California Two Spot Octopus (Octopus Bimaculoides).
Classifying and understanding animal behavior has been a hot-topic endeavor of biologists since even before the great Charles Darwin, but historically has very often been assays with pen on paper note taking. With recent developments in both the processing power of your average computer and the mathematics behind this processing, machine-learning has sprung up as a powerful tool to help us see beyond what our brains can comprehend. We now have the novel ability to find patterns in everything from the behaviors of lab rats or communication of cuttlefish chromatophores without having to introduce the arduous task of a scientist to list through thousands of frames of video.
With my project I plan to do exactly this, to collect a plethora of video data of Bimac Octopodes and use computer-vision and machine-learning techniques to extract behaviors from this video without biasing it via human intervention.
Below is an example of some of my work so far; using background subtraction, erosion, and Gaussian filtering I am able to transform a recording of a moving animal (in this case a squid) into an easily trackable contour entity, and then create a graph of its movement pattern (on the bottom).
Additionally, I have a working algorithm to detect and quantify breathing patterns in a resting octopus. It transforms the video stream of the octopus (top) into a graph of detected motion vs frame number (center), which when then smoothed with the Blackman-Harris window function, allows us easily to deduce the time between breaths, in this case, 6.67 seconds (bottom).
I hope to continue to develop tools for octopus video analysis in this coming month and to discover more and more the hidden patterns in this beautiful animal’s behavior. I am especially excited to look into quantifying their problem-solving skills through various intellect challenging exercises (like letting them explore a maze!).