Abstract

The data was collected by outfitting one of the players with the experimental balloon, which incorporated the embedded circuit and sensors. The sensors positioned at the top-right to the player within the bubble balloon, where a player stand inside. The sensors' data were collected at specific sampling frequencies (Accelerometer: 1000Hz, Gyroscope: 1000Hz, and Pressure: 40Hz). The experiment was conducted involving five different players. This approach allowed for the inclusion of diverse data samples, taking into account variations in player metrics, movements, and gameplay dynamics. This dataset includes 173 falls, providing a suitable dataset for analysis and evaluation of the fall detection system. The falls were labelled at real time during play within the time stamps. A label value of 1 indicates a fall event, while a value of 0 represents a non-fall event. It is worth emphasizing that the duration of each fall event varies.

Instructions:

1. upload and open "Fall_Detection_Data_Visualization.ipynb" in colab.

2. upload the dataset file " labeled_fall_detection_data.pkl " to the notebook . Also, upload the file "all_labels.json" to see the duration time for each fall.

3. The script has the functions to read the data file, extract the data for each sensor, and plot data for visualization.

4. For furture processing data, the following variables contain the raw data :

- acc_x, acc_y, acc_z: represent the accelerometer data.

- gyr_x, gyr_y, gyr_z: represent the gyroscope data.

- pressure: represents the pressure sensor data.

- label : data labels (fall =1; non-fall=0).

5. when you run the code, you will see plots (you can modify timing to check different time stamps);

Note The dictionary of the dataset is : dict_keys(['time', 'acc_x', 'acc_y', 'acc_z', 'gyr_x', 'gyr_y', 'gyr_z', 'pressure', 'label'])

Datasets

Standard Dataset

Fall Detection in Q-eBall

Abstract

Dataset Files

QUESTIONS?