Multitask Deep Learning for Human Activity, Speed, and Body Weight Estimation Using Commercial Smart Insoles

Abstract

Healthcare professionals and individual users use wearable devices equipped with various sensors for healthcare management. Recently, the joint usage of artificial intelligence and these wearable sensors has played an essential role in healthcare management by providing a wide range of applications such as fitness tracking, gym activity monitoring, patient rehabilitation monitoring, and disease detection. These tasks eventually aim to enhance personal well-being and better manage the user's physical health by monitoring different activity types and body weight changes. Here, we present an efficient multi-task learning framework based on commercial smart insoles that can solve three tasks related to physical health management: activity classification, speed estimation, and body weight estimation. Our multi-task framework converts the sensor data from the smart insole to a recurrence plot, which shows significant performance improvement compared to processing the raw time series data. In addition, we utilized a modified MobileNetV2 as our backbone network, which has a total parameter of less than 100K and a computational budget of 0.34G of multiply-accumulate operations. Furthermore, we collected a vast dataset from 72 users carrying out 16 experiments, which contains the largest number of people for multi-task learning purposes using smart insoles. Extensive experiments show that the proposed multi-task learning framework is extremely efficient while outperforming or leading to comparable performance against single-task models.

Validation of the Short Physical Performance Battery via Plantar Pressure Analysis Using Commercial Smart Insoles

“…Previous studies have demonstrated that these devices accurately measure changes in plantar pressure during walking [ 21 ]. Additionally, it has been revealed that they can be utilized for real-time walking speed estimation, weight estimation, and activity classification [ 12 ]. For this study, we obtained a program from the manufacturer to receive real-time plantar pressure data.…”

“…Smart insoles capable of capturing real-time measurements of plantar pressure during everyday activities have been introduced and made available in the market at reasonable prices [ 12 , 13 ]. Since the inception of smart insoles, numerous studies have explored their applications in the medical field.…”

An Individualized Machine Learning Approach for Human Body Weight Estimation Using Smart Shoe Insoles

“…compared to the MAE of 15.10 lbs. achieved by Kim et al in [10]. This is because the pro- Table 6 illustrates the performance analysis of the proposed method on both the environmental settings with respect to the existing state-of-the-art method.…”

“…achieved by Kim et al in [10]. This is because the proposed method generates a personalized model for every participant rather than using the whole dataset to train a single machine learning model as performed in [10].…”

“…Kim et al [10] proposed a modified MobileNetV2 architecture-based multi-tasking deep learning model for classifying human activities and estimating speed and body weight using the shoe insole sensors of 72 participants. The inputs given to the model comprise the signal data, such as acceleration and pressure, extracted from the insole sensors.…”