Human activity recognition using machine learning techniques in a low-resource embedded system
Resumen:
Human activity recognition aims to infer a person’s actions from a set of observations captured by several sensors. Data acquisition, processing and inference on edge devices add a complexity factor to the task, as they involve a trade-off between hardware efficiency and performance. We present a prototype of a wearable device that identifies a person’s activity: walking, running or staying still. The system consists of a Texas Instruments MSP-EXP430G2ET launchpad, connected to a BOOSTXL-SENSORS boosterpack with a BMI160 accelerometer. The designed prototype can take acceleration measurements, process them and either transmit them to a computer or classify the activity in the microcontroller. Additionally, our system has LEDs to display coloured signals according to the inferred activity in real-time. The classification algorithm is based on the calculation of statistical features (mean, standard deviation, maximum and minimum) for each accelerometer axis, the application of a dimensionality reduction algorithm (LDA, Linear Discriminant Analysis) and an SVM (Support Vector Machines) classification model.
| 2021 | |
| Este trabajo fue parcialmente financiado por la Comisión Académica de Posgrado (CAP, UdelaR), Espacio Interdisciplinario (EI, UdelaR) y la Comisión Sectorial de Investigación Científica (CSIC, UdelaR) “Proyecto I + D : Sistema electrónico para la caracterización del comportamiento de ovinos". | |
|
Human Activity Recognition Acceleration Sensor Linear Discriminant Analysis Support Vector Machines |
|
| Inglés | |
| Universidad de la República | |
| COLIBRI | |
| https://hdl.handle.net/20.500.12008/30548 | |
| Acceso abierto | |
| Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
| Sumario: | Human activity recognition aims to infer a person’s actions from a set of observations captured by several sensors. Data acquisition, processing and inference on edge devices add a complexity factor to the task, as they involve a trade-off between hardware efficiency and performance. We present a prototype of a wearable device that identifies a person’s activity: walking, running or staying still. The system consists of a Texas Instruments MSP-EXP430G2ET launchpad, connected to a BOOSTXL-SENSORS boosterpack with a BMI160 accelerometer. The designed prototype can take acceleration measurements, process them and either transmit them to a computer or classify the activity in the microcontroller. Additionally, our system has LEDs to display coloured signals according to the inferred activity in real-time. The classification algorithm is based on the calculation of statistical features (mean, standard deviation, maximum and minimum) for each accelerometer axis, the application of a dimensionality reduction algorithm (LDA, Linear Discriminant Analysis) and an SVM (Support Vector Machines) classification model. |
|---|
