Seal Sleep Capstone
Scripts
File Size |
|
File Format |
|
Scope And Content | Follows data science cookie-cutter format, analysis pipeline with feature extraction and model building, as well as frontend product development in the marine-somniac sub-folder. |
Technical Details |
Python 3.10 for model building and 3.11 for product development (but product should be compatible with 3.10). |
Output file
File Size |
|
File Format |
|
Scope And Content | Output of the pipeline are three different models trained with LightGBM for classifying sleep scoring on seals. |
Technical Details | LightGBM |
- Collection
- Cite This Work
-
Sorenson, Michael A.; Song, Melody Q.; Basic, Tarik; Rajput, Yousuf W.; Tarif, Tarek R.; Kendall-Bar, Jessica; Altintas De Callafon, Ilkay (2024). Seal Sleep Capstone. In Data Science & Engineering Master of Advanced Study (DSE MAS) Capstone Projects. UC San Diego Library Digital Collections. https://doi.org/10.6075/J0R49QZ9
- Description
-
As part of the DSE MAS Data Science program, we constructed a project with the goal of to develop a machine learning framework capable of accurately classifying sleep states in Northern Elephant Seals. The data used included electrophysiological and motion data collected from the seals, comprising EEG (electroencephalogram) and ECG (electrocardiogram) signals, along with motion data from gyroscopes and pressure sensors. These data were gathered using custom non-invasive head caps and waterproof housings and were manually labeled for sleep, behavioral, and respiratory stages by experts. The raw signal data was provided in EDF format, and the labels were in CSV files with corresponding timestamps. This rich dataset enabled the extraction of key features necessary for training and evaluating the machine learning models.
- Scope And Content
-
Download input data from Kendall-Bar, Jessica et al. (2023). Data for: Brain activity of diving seals reveals short sleep cycles at depth . Dryad. https://doi.org/10.7291/D1ZT2B.
The data is a set of raw .edf files containing data on seals; seals are split by name (e.g. "test12_Wednesday") and each file is split by day (e.g. "DAY0", "DAY1", "DAY2", etc.). Each seal also has its own hypnogram file, containing sleep labels per second. - Date Collected
- 2024-01-15 to 2024-06-07
- Date Issued
- 2024
- Advisors
- Contributors
- Note
-
This project relies on external software packages, modules/libraries, or programs, use of which may carry specific license requirements. Users should comply with any licenses specified within the contents of this project.
- Series
- Topics
-
- Behavioral analysis
- Biological sciences
- Capstone projects
- Data Science & Engineering Master of Advanced Study (DSE MAS)
- Ecology
- Electrophysiology
- Machine learning
- Marine biology
- Neurophysiology
- Northern elephant seals
- Polysomnography
- Sleep classification
- Task: Classification
- Task: Feature extraction
Formats
View formats within this collection
- Language
- English
- Related Resources
- Kendall-Bar, Jessica et al. (2023). Data for: Brain activity of diving seals reveals short sleep cycles at depth [Dataset]. Dryad. https://doi.org/10.7291/D1ZT2B
- Capstone repository https://github.com/jmkendallbar/Seal-Sleep-Capstone
- Kendall-Bar, JM; Williams, TM; Mukherji, R; Lozano, DA; Pitman, JK; Holser, RR; Keates, T; Beltran, RS; Robinson, PW; Crocker, DE; Adachi, T; Lyamin, OI; Vyssotski, AL; Costa, DP (2023). Brain activity of diving seals reveals short sleep cycles at depth. Science. https://doi.org/10.1126/science.adf0566
Source data
Software
Reference
- License
-
Creative Commons Attribution 4.0 International Public License
- Rights Holder
- Sorenson, Michael A.; Song, Melody Q.; Basic, Tarik; Rajput, Yousuf W.; Tarif, Tarek R.
- Copyright
-
Under copyright (US)
Use: This work is available from the UC San Diego Library. This digital copy of the work is intended to support research, teaching, and private study.
Constraint(s) on Use: This work is protected by the U.S. Copyright Law (Title 17, U.S.C.). Use of this work beyond that allowed by "fair use" or any license applied to this work requires written permission of the copyright holder(s). Responsibility for obtaining permissions and any use and distribution of this work rests exclusively with the user and not the UC San Diego Library. Inquiries can be made to the UC San Diego Library program having custody of the work.
- Digital Object Made Available By
-
Research Data Curation Program, UC San Diego, La Jolla, 92093-0175 (https://lib.ucsd.edu/rdcp)
- Last Modified
2024-07-18