ADANet GestureMotion: Human Accelerometer Dataset for Real-Time Gesture Recognition
- Citation Author(s):
-
MD Ettashamul Haque
Atique Tajwar
Md Mehedi Hasan
- Submitted by:
- MD Ettashamul Haque
- Last updated:
- DOI:
- 10.21227/2cs0-j680
45 views
- Categories:
- Keywords:
Abstract
This dataset comprises high-resolution 3-axis accelerometer recordings collected from human participants performing distinct hand gestures, intended for training gesture-based assistive interfaces. Each participant’s raw motion signals are individually organized, enabling both user-specific and generalizable model development. The dataset includes time-series accelerometer data, along with a feature-augmented version containing extracted statistical and temporal descriptors such as RMS, Jerk, Entropy, and SMA.
Instructions:
The dataset contains raw 3-axis accelerometer recordings from multiple participants performing distinct gestures, organized in the Dataset/ folder. Pre-split training, validation, and test sets are available in Splitted_Dataset/. To preprocess, use Preparing_Dataset.ipynb to extract statistical and temporal features; for custom splits, use Dataset_Split.ipynb. The processed features are ready for training models like ADANet or traditional classifiers. Consistent random seeds are recommended for reproducible results.
