Apollo Smart Walker Dataset

APOLLO SMART WALKER DATASET

Gait monitoring of elderly people who use walkers.
This dataset collects data from the accelerometer, gyroscope and magnetometer sensors of the smartphone positioned in the center of a walker.

ADL 1
Forward: Starting the walk on the sidewalk, passing through the grass to the end point.
Backward: Starting the walk on the grass, going to the sidewalk.

ADL 2
Forward: Starting the walk from an internal environment of the house and going to the external environment.
Backward: Starting the walk from an external environment of the house and going to the internal environment.

ADL 3
Forward: Starting the walk in the living room, going through the hallway and entering the bathroom.
Backward: Starting the walk in the bathroom, going through the hallway and entering the living room.

See the records of this dataset:
ADL 1 https://www.youtube.com/playlist?list=PLRHcq8YHj4-aHt03LLV-tvM9IP90869dU
ADL 2 https://www.youtube.com/playlist?list=PLRHcq8YHj4-YaOt1KNg5KhCxcO1wuF_F_
ADL 3 https://www.youtube.com/playlist?list=PLRHcq8YHj4-YEc2PifRcFp0Aw1AJFIuXC

Number of samples: 180
Number of Instance: 482031
Data Set Characteristics: Sequential Data, Time Series Data, Multivariate Data, Correlation
Area: Elderly Health, Applied Computing
Attribute Characteristics: Integer, Double
Number of Attributes: 5

The coordinate-system is defined relative to the screen of the phone in its default orientation. The axes are not swapped when the device's screen orientation changes.
The X axis is horizontal and points to the right, the Y axis is vertical and points up and the Z axis points towards the outside of the front face of the screen. In this system, coordinates behind the screen have negative Z values.
Source: https://developer.android.com/reference/android/hardware/SensorEvent

Apollo Smart Walker Collector github repository:
https://github.com/hartmannjean/Apollo-Smart-Walker-Collector

Relevant Information:
1. The dataset collects data from an Android smartphone which is positioned in the center of the walker;
2. The data sensors collected are accelerometer, gyroscope and magnetometer;
3. The sampling frequency of the sensors is DELAY_FASTEST - 20 milliseconds;
4. Data format: CSV.

Dataset information:
1. Dataset was recorded in video;
2. The dataset was recorded in three different scenarios. Each scenario has two turns, going forward and coming back.
3. Each scenario was recorded 20 times.
4. Each recording generated three files:
i. Accelerometer;
ii. Gyroscope;
iii. And magnetometer;
5. Each file contains the following information;
i. Timestamp, Id, x axis, y axis, z axis.

This dataset is part of this article paper:
Hartmann, Jean; Tavares, João (2022). Apollo Smart Walker: A Model Based on IoT and Artificial Intelligence for Monitoring the Gait of Elderly People Using Walkers.
Universidade do Vale do Rio dos Sinos.