Human Fall Detection using Accelerometer and Gyroscope Sensors in Unconstrained Smartphone Positions

Abstract

This study explored several methods for detecting body falls based on the data captured by the sensors (accelerometer and gyroscope) built in a smartphone carried by a person. The data for this study were collected by recording many sample units from each of the following human activity categories: stand-fall, walk-fall, stand-jump, stand-sit, stand, and walk. Several time-series data captured by the sensors were used as human motion features. One of the challenges of this study was the existence of human body motions whose features resembled those of body falls. In addition, unfixed smartphone positioning made human body falls harder to detect and can lead to high rate of misclassification (not detected as fall). This incident can caused serious bone fracture or even death if the person not handled as immediately as possible because of misclassification. To address this problem, we modified Resultant Acceleration and ∠ Y formulas to address the problem of unconstrained smartphone positions. We proposed to combine five methods such as AGVeSR, Alim, ∠α, GyroReDi, and AGPeak to build a robust detector model to reduce the misclassification. The experiment results showed that the accuracy of the combination of both sensors (accelerometer and gyroscope) outperformed the accuracy of accelerometer only by more than 15%. The decision fusion that used voting involving five methods could boost the accuracy rate by up to 4.15%

Design and build an airbag system for elderly fall protection using the MPU6050 sensor module

“…The angle formed is not 90 o , but rather slightly tilted from a right angle depending on the falling motion. In addition to the angle, the angular velocity of the sensor is also considered [22], [23]. The angular velocity formula is similar to the angular change formula, but using the pitch and roll gyro values in (3).…”

Analysis of waist and wrist positioning wearable machine learning models to detect falls

“…This is why we opted to utilize the accelerometer and gyroscope data from the FallAllD dataset [8] to train, validate, and test the selected ML models. Sensor data fusion is important to obtain better results, as reported in [9], there was an increase of 15% in accuracy when using both sensors. [10] states that the accelerometer suffers from external vibrations, such as user trembling, resulting in inaccurate orientation estimations, consequently by fusing data from a gyroscope or a magnetometer one can prevent these inaccurate estimations.…”

Consumer privacy in smartphones: a systematic literature review

“…Next-generation communication technologies accelerated the adoption of smartphones as the primary medium for consumer interactions (Steen, 2009; Kim and Park, 2016). Smartphones provide technology convergence of internet, camera, microphone, location sensors, orientation sensors, fingerprint and other biometric sensors, among others (Gábor and Gausz, 2018; Astriani et al , 2019; Roobini and Fenila Naomi, 2019; Söderlund et al , 2019; Subasi et al , 2019; Sukariasih et al , 2019; Petrescu et al , 2020). This technology convergence is one of the key contributing factors making smartphones the preferred target for genuine and malicious actors.…”