The B-SOiD algorithm is able to discover types of movements, as depicted in the cloud of points here, and then generalize across subjects, detecting the same movements in both individuals.
B-SOiD is an open source, unsupervised algorithm that can discover and identify behaviors without user input
To Eric Yttri, assistant professor of biological sciences and Neuroscience Institute faculty at Carnegie Mellon University, the best way to understand the brain is to watch how organisms interact with the world.
“Behavior drives everything we do,” Yttri said.
As a behavioral neuroscientist, Yttri studies what happens in the brain when animals walk, eat, sniff or do any action. This kind of research could help answer questions about neurological diseases or disorders like Parkinson’s disease or stroke. But identifying and predicting animal behavior is extremely difficult.
Now, a new unsupervised machine learning algorithm developed by Yttri and Alex Hsu, a biological sciences Ph.D. candidate in his lab, makes studying behavior much easier and more accurate. The researchers published a paper on the new tool, B-SOiD (Behavioral segmentation of open field in DeepLabCut), in “Nature Communications.”
Previously, the standard method to capture animal behavior was to track very simple actions, like whether a trained mouse pressed a lever or whether an animal was eating food or not. Alternatively, the experimenter could spend hours and hours manually identifying behavior, usually frame by frame on a video, a process prone to human error and bias.
Hsu realized he could let an unsupervised learning algorithm do the time-consuming work. B-SOiD discovers behaviors by identifying patterns in the position of an animal’s body. The algorithm works with computer vision software and can tell researchers what behavior is happening at every frame in a video.
“It uses an equation to consistently determine when a behavior starts,” Hsu explained. “Once you reach that threshold, the behavior is identified, every time. A human experimenter might toggle between two frames or several categories, try to decide where behavior begins and become fatigued over time.”
Yttri said B-SOiD provides a huge improvement and opens up several avenues for new research.
“It removes user bias and, more importantly, removes the time cost and arduous work,” he said. “We can accurately process hours of data in a matter of minutes.”
Additionally, B-SOiD is very user friendly and openly available to any researcher. Yttri’s lab and their collaborators have used the new algorithm in research on many important areas, including research to better understand chronic pain, obsessive compulsive disorder and more.
Collaborators have even begun to use B-SOiD to study human movement in Parkinson’s disease.
“We are beginning to see if this can be used as part of an objective test by a doctor to show how far a patient’s disease has progressed. The hope is that a patient anywhere in the world would be diagnosed with one standardized metric,” Yttri said.
This is a breakthrough in how scientists can study natural behavior and how it changes rather than the overly simplistic or subjective measures that predominate neuroscience and ethology.
Original Article: Machine Learning Algorithm Revolutionizes How Scientists Study Behavior
More from: Carnegie Mellon University
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Study of behavior
- University of Mississippi graduate studies human behavioron October 23, 2021 at 10:00 pm
University of Mississippi graduate Christopher Patton loves exploring the way people think and behave and he gets to use his expertise to help Facebook create a better ...
- Belief in COVID-19 conspiracy theories linked to a greater likelihood of contracting the virus, study findson October 22, 2021 at 1:11 pm
"Conspiracy theories are in many ways harmful for society. But, this study suggests that in the long run, conspiracy theories also are associated with harmful health and well-being outcomes for ...
- Study maps neurons essential for social behavior and healthy relationships within groupson October 21, 2021 at 11:24 pm
Meaningful social interactions are critical to an individual's well-being, and such interactions rely on people's behaviors towards one another.
- New study unravels the origins of innate behavior in flieson October 21, 2021 at 9:17 am
Human babies are born knowing how to suckle, and larval flies hatch knowing how to crawl. But even these innate behaviors don’t appear out of nowhere. Patterned waves of brain activity during ...
- Global Classroom Behavior Management Software Market 2021 SWOT Study, Sales Analysis, Technological Innovations and Competitive Landscape to 2027on October 19, 2021 at 12:34 pm
Another report by named, Global Classroom Behavior Management Software Market 2021 by Company, Regions, Type and Application, Forecast to 2027 has been added into its tremendous archive by ...
Go deeper with Google Headlines on:
Study of behavior
Go deeper with Bing News on:
- Eating Disorders and Social Media Prove Difficult to Untangleon October 23, 2021 at 7:19 am
A 27-year-old YouTube star, prodded by her millions of followers with concerns about her health. A 19-year-old TikTok creator who features posts about being skinny. Teen communities throughout the ...
- On Faith: Algorithms, AI and amoralityon October 22, 2021 at 9:00 pm
Thank you, Frances Haugen. For anyone who has been living under a rock, Ms. Haugen is the ex-Facebook employee who has gone public about how Facebook’s algorithms are designed in ...
- Facebook-Created Fake Users Proved Algorithm Radicalized People in 2019on October 22, 2021 at 8:41 pm
Leaked documents shared NY Times, CNN, NBC and others also show Facebook was unprepared for the spread of lies and conspiracy about the 2020 Election ...
- Safiya Noble Knew the Algorithm Was Oppressiveon October 21, 2021 at 7:48 am
At the heart of the author and scholar’s work is the assertion that racism and sexism are baked into algorithms: “The world is becoming more unequal, and technologies are implicated in that.” ...
- Autoliv uses HERE to analyze driving behavioron October 21, 2021 at 1:00 am
Autoliv uses HERE to analyze driving behavior World's largest automotive safety supplier uses HERE location data to enhance its Safety Score, a driving behavior analysis tool for fleet managers and ...