Hello all! The summer fellowship is officially over, but it’s not quite the end of the line for the jellies and me! In this final(?) update to my blog series I’ll be recalling the findings I’ve made over this summer, showcasing the poster I presented at the UROP Symposium, sharing my road trip back home (with the jellies in tow!!!), and planning my post-fellowship jellyfish-based research!
Final Fellowship Findings:
I’ve learned a lot about clytia hemisphaerica over this fellowship. This ranges from their appearance and life stages (polyp, ephyrae, medusa) to their husbandry and maintenance needs (acceptable salt levels, daily and weekly water changes, feeding requirements). This newfound knowledge also includes their behaviors and abilities, like how they catch and eat prey or how they dart, zig-zag, and make circles in the water. I have collected a decent number of videos for my jellyfish dataset, and I’ve done some basic position tracking on most of that dataset, but unfortunately the fellowship was over before any rigorous analysis could be completed.
However, this is not the end! I will be dedicating time over the next few weeks to progressing my research by adding features to my jellyfish tracking/analysis software to get more usable stats on the videos, by analyzing jelly video stats using unsupervised machine learning for labeling behaviors, and by getting more raw footage of these wonderful jellies to add to the dataset! (But more on that later.)
This first photo is of the poster I made for and presented at the UROP symposium. It gives a brief introduction on clytia hemisphaerica, explains how I created my dataset (video recordings), and shows what observations and findings were made.
This next photo shows the poster and me in action at the symposium!
I got to meet a lot of exciting people and shared endless amounts of unusual jellyfish facts with them. [Example fun fact: Did you know it’s been confirmed that some jellyfish (like the upside down jellyfish) sleep? This finding by researchers at Caltech (http://www.sciencemag.org/news/2017/09/you-don-t-need-brain-sleep-just-ask-jellyfish) was surprising since jellyfish don’t have brains or even a central nervous system, so sleep must be a more universal activity than previously thought.]
Jelly Road Trip:
The day came much too quickly – the day I had to leave Ann Arbor and go back home to Cincinnati. I spent 7 hours straight packing and loading the car with all the things I’d brought with me or accumulated during my stay.
There was a lot of stuff and it took up a lot of (hard to find) space in my compact-size sedan, but one spot remained clear: the passenger seat.
The passenger seat was reserved for the 2 remaining jellies! I got approval to take them home with me and continue my work in Cincinnati! After 220 miles of highway roads, the jellies finally got to see their new home (and I got to improvise a new DIY tank setup).
Now that the jellies are here, we can start on the post-fellowship jellyfish-based research plans!
Over the next few weeks, I plan to make more recordings of the jellyfish in a wider variety of situations. I’ll try changing environmental variables like lighting, current direction/intensity, salinity, and water temperature.
Some of the features I plan to add to the tracking/analysis software include optical flow options (to track the water current based on the dust particles visible in the videos), ellipse fitting options (to gauge when the jellyfish is actively pulsing), and multiple jelly support (for tracking 2 or more jellyfish at once).
Finally, the machine learning portion of this project will revolve around mostly unsupervised methods in the hopes that behaviors can be found with minimal bias and human error. Some options that were discussed include basic k means clustering as a start followed by other methods like compressing the layers of the neural network to force the algorithm to find patterns that effectively store the original data without losing any information.
This fellowship was a great experience and I’m very excited and grateful for the opportunity to bring my project home with me and continue my research.
Welcome back, fellow Jelly-Lovers! We’ve got lots of exciting jellyfish-based updates below, including revealing videos of our very own clytia hemisphaerica, screenshots from and updates about the tracking software, and information on our new recording chamber. (And, of course, I have photos of the full jellyfish costume from the 4th of July!)
As promised, we will start off with some delightful, ultra-short films starring the infamous clytia hemisphaerica. The first 30-second clip shows a super close-up view of a jellyfish that has caught its prey (brine shrimp). The following 48-second clip displays the varying stages of tentacle length in these tiny jellies (their tentacles elongate and retract at will – you have to see it to believe it!!!).
Above you will find a short video showcasing a few clips of a jellyfish that has caught several brine shrimp! Considering that this full-grown jellyfish is less than 20mm in diameter, the zoomed-in details and quality are easily better than what you would see in the real world with the naked eye!
This second video exhibits the 3 different tentacle states I’ve observed: fully extended/elongated, partially retracted, and fully retracted. It seems that the tentacles become longer and more spread out when the jellyfish is hunting (trying to catch brine shrimp). This behavior would make sense, since elongating/spreading out the tentacles would increase the jelly’s area of coverage and therefore raise its chance of success in finding a fresh meal.
Since I received this batch of jellyfish and got them stable in their new homes, I’ve recorded well over 60 trial videos with which to analyze their behaviors. To get a head start on analyzing this data, I decided to try labeling a video by hand. I briefly labelled a 25-minute clip manually to see what the data would look like, and after 2 hours had only labeled 3 minutes-worth of frames. This showed me just how inefficient and impossible this task is without some form of computerized help, like that of the in-development jellyfish tracker.
The screenshot above is packed full of useful information from a video run through the jellyfish tracker. The top left shows a close-up image centered on the tracked jellyfish. The text boxes near the top of the screenshot show properties like frame height/width, frame rates, and total frame counts. The ‘Final Coordinates’ table lists the jellyfish’s position within the video. Finally, the graphs show the X position over time, the Y position over time, and the X vs Y position (the jellyfish’s location in 2D space).
The jellyfish-tracking software can now track jellies somewhat accurately (thanks to Stan’s immense help), if given a clean trial video as input. However, slight imperfections in lighting and other environmental variables throw the tracking algorithm off, so the software is not yet robust enough for all the trial footage collected. More tracking algorithm adjustments and video pre-processing steps need to be coded before the software is fully ready.
New Recording Chamber:
Part of the problem I ran into while doing recordings for different trials was control and reproducibility of environmental variables (like lighting) and protecting the water from external air-borne contaminants. A reusable, enclosed testing chamber seemed to be a good solution for my problems.
The first recording chamber was the inside of a cabinet (pictured below).
While it was better than nothing, the cupboard setup was not consistent: there was nothing to hold the petri dish/phone in the same position each trial. Also, having to duct tape the phone (our recording device) for each recording was quite time-consuming (not to mention a gamble as to whether the phone was turned on, auto-focused, or even recording during the trial since the screen was facing the shelf). On top of these problems, the cupboard was in a small closet-type room that does not allow for too many people inside, and the room was often in use by others. It became apparent that a better recording chamber needed to be manufactured.
The photo above shows the progression from pieces of scattered plywood to the new, mobile recording enclosure. This setup is much more consistent and solves most of the problems I’ve listed with the previous attempts.The bottom of the recording chamber has a circular cut-out that is barely larger than the petri dish used for 2D recordings, so placement of the dish is consistent each time. There is a rectangular opening in the front through which everything gets placed (petri dish, sea water, jellyfish and all) which is covered by a black cloth when not being used in an attempt to limit external contamination. This cloth also blocks out the light in whatever room the recording chamber is in, so lighting can be consistent across trials. The hole in the top of the chamber is where the camera goes, and since the phone is placed face-up over the recording hole, we can start/stop recordings, focus the video, and see what’s going on inside the recording chamber during the entire trial! Also, this contraption is mobile, so I can record wherever I need without worrying that a specific room would be in use.
My DIY Jellyfish Costume:
Finally, I’ve added some photos of my homemade costume from the 4th of July, which you may have already seen in another post on the BYB blog: in my previous update, I previewed the costume and the Fellows Summer Experience post showed it as well!
Hello all! My name is Anastasiya and I’m a computer engineering and neuroscience double major at the University of Cincinnati. I’m curious about the world around me and my favorite thing to do is learn. My hobbies include making strange noises, fangirling over the fuel efficiency of my car, and volunteering while spreading knowledge to the general public. I mainly volunteer at the Cincinnati Observatory, home of the oldest professional telescope open to the public, and at Cincinnati Public Schools, where I help out with a Lego League robotics club and mentor a group of high school scholars.
This summer I’m investigating ‘The Secret Life of Jellyfish’, specifically, of the clytia hemisphaerica. They’re super tiny (they max out at about 20mm in diameter) and seem to be capable of doing things they shouldn’t be able to do. By that I mean that these jellyfish seem to exhibit relatively complex behaviors without making use of a brain (since they don’t have one). They’re also kind of ridiculous and paradoxical to me, because trying to lift one out of the water could easily kill the clytia since the surface tension of the water is too much for it to handle, but you can chop it in half and it’ll be just fine as two separate jellies. Weird (but cool)!
The current plan is to record videos of the jellyfish in various situations and then use some form of machine learning to figure out the jellies’ behavior. I’ve looked at some potential tracking software, libraries, and random snippets of code, and it seems that OpenCV is my best bet for analyzing the videos, so I’ve spent the last couple weeks learning about it and how to use it in Visual Studio 2017 with C++. But learning about code is not all I’ve done; I’ve also been preparing for the impending arrival of clytia hemisphaerica to our laboratory.
I first made sure to get a (hopefully) decent environment set up for them. Clytia hemisphaerica need salt water at a salinity of 1.0268, or 37 parts per thousand, and a small current to keep them swimming as this is critical to their health. The housing units I set up are based on the traditional beaker method and include 3.7L beakers (actually 6”x8” glass vases from Amazon) filled with artificial sea water as well as a constant current stimulator made of acrylic rectangles, hot glue, plastic pipettes, 12V 5RPM motors, some wires, and an AC to DC adapter. All of these things together should provide a nice home for the jellies when they arrive, but that is not all I need to prepare.
Jellyfish, like many living things, need a food source, and the one I’m preparing is artemia, otherwise known as brine shrimp. Brine shrimp are pretty easy to hatch, and just one cap-full of brine shrimp eggs makes a very large amount of baby brine shrimp, enough to turn an entire bottle and beaker a shade of orange. That must mean that, after a one-time investment of a large batch of artemia, I am all set on jellyfish food for the summer, right? Well, there’s a catch. The catch here is that clytia hemisphaerica should only eat 1.5 to 4 day old brine shrimp, and eating ones that are are outside this age range for prolonged periods of time could have deadly consequences for the poor jellies (and for my easily over-attached heart). This means I’ll have to constantly hatch and culture new batches of brine shrimp and keep track of hatch dates so I have the proper feed for these picky eaters.
At this point, I’m pretty sure everything is ready for the jellies to come in, and they should be gracing us with their presence any day now. I’m very excited to be working on this project as a fellow at Backyard Brains, and I can’t wait to see these jellyfish in person! The more I learn about them, the more mysterious and intriguing clytia hemisphaerica become, and I look forward to finding at least some pieces to the puzzle that is their behavior.