A database of human gait performance on irregular and uneven surfaces collected by wearable sensors

Abstract

Gait analysis has traditionally relied on laborious and lab-based methods. Data from wearable sensors, such as Inertial Measurement Units (IMU), can be analyzed with machine learning to perform gait analysis in real-world environments. This database provides data from thirty participants (fifteen males and fifteen females, 23.5 ± 4.2 years, 169.3 ± 21.5 cm, 70.9 ± 13.9 kg) who wore six IMUs while walking on nine outdoor surfaces with self-selected speed (16.4 ± 4.2 seconds per trial). This is the first publicly available database focused on capturing gait patterns of typical real-world environments, such as grade (up-, down-, and cross-slopes), regularity (paved, uneven stone, grass), and stair negotiation (up and down). As such, the database contains data with only subtle differences between conditions, allowing for the development of robust analysis techniques capable of detecting small, but significant changes in gait mechanics. With analysis code provided, we anticipate that this database will provide a foundation for research that explores machine learning applications for mobile sensing and real-time recognition of subtle gait adaptations.

BLE-GSpeed: A New BLE-Based Dataset to Estimate User Gait Speed

“…For example, Fukuchi et al [36] developed a database with detailed kinematic information of 42 healthy volunteers; similarly, Schreiber et al [37] performed a similar experiment measuring the GS in 50 free-injury participants. Custom high-precision inertial sensors have also been used in [38], focusing on the age difference, and in [39], with the focus on detecting changes in the gait mechanics. All these databases are focused on the health relation between GS and other parameters.…”

Research on the Advantages of Digital Sensor Equipment in Language Audio‐Visual and Oral Teaching

“…Feng and Pan proposed using principal component analysis technology to reduce the dimension of mean, variance, and frequency domain features and using decision tree as classifier for classification [3]. In addition, Luo and Xiao use the compressed sensing method to efficiently process low dimensional sampling data for classification [4,5]. In 2013, researchers from the University of Catalonia in Spain and the University of Genoa in Italy identified six behaviors such as walking, sitting, and standing by using the built-in sensors of mobile phones and disclosed the data set recorded in the experiment to volunteer researchers [6].…”

Towards Fuzzy Context-Aware Automatic Gait Assessments in Free-Living Environments

“…The duration of each walking trial was on average 16.4 ± 4.2 s. Feature Extraction. Because the long term goal is to perform outdoor surface classification based on data collected using a smartphone, only accelerometer and gyroscope data from the lower back IMU (emulating smartphone) were included in the analysis; more specifically, Acc X, Acc Y, Acc Z, Gyr X, Gyr Y and Gyr Z channels provided in the data.mat file in [17]. These channels provided raw sensor data which were low-pass filtered 6 Hz cut-off frequency.…”