A Multilayer Interval Type-2 Fuzzy Extreme Learning Machine for the recognition of walking activities and gait events using wearable sensors

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human-computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

A type-2 fuzzy index to assess high heeled gait deviations using spatial-temporal parameters

This paper introduces an intelligent index that numerically assesses high-heeled gait deviations. Experiments were conducted on 14 young female volunteers, and the spatial-temporal gait parameters were calculated at each heel height. A type-2 fuzzy system index was built using the baseline case (barefoot). The index showed sensitivity to heel height changes. Moreover, its values divided the heel heights used in this study into three groups, depending on their effect on the gait parameters. A high correlation between the proposed index and the gait profile score (GPS) was found, this supports the index validity to evaluate different human gait deviations.

Locomotion Mode Recognition Algorithm Based on Gaussian Mixture Model Using IMU Sensors

The number of elderly people has increased as life expectancy increases. As muscle strength decreases with aging, it is easy to feel tired while walking, which is an activity of daily living (ADL), or suffer a fall accident. To compensate the walking problems, the terrain environment must be considered, and in this study, we developed the locomotion mode recognition (LMR) algorithm based on the gaussian mixture model (GMM) using inertial measurement unit (IMU) sensors to classify the five terrains (level walking, stair ascent/descent, ramp ascent/descent). In order to meet the walking conditions of the elderly people, the walking speed index from 20 to 89 years old was used, and the beats per minute (BPM) method was adopted considering the speed range for each age groups. The experiment was conducted with the assumption that the healthy people walked according to the BPM rhythm, and to apply the algorithm to the exoskeleton robot later, a full/individual dependent model was used by selecting a data collection method. Regarding the full dependent model as the representative model, the accuracy of classifying the stair terrains and level walking/ramp terrains is BPM 90: 98.74%, 95.78%, BPM 110: 99.33%, 95.75%, and BPM 130: 98.39%, 87.54%, respectively. The consumption times were 14.5, 21.1, and 14 ms according to BPM 90/110/130, respectively. LMR algorithm that satisfies the high classification accuracy according to walking speed has been developed. In the future, the LMR algorithm will be applied to the actual hip exoskeleton robot, and the gait phase estimation algorithm that estimates the user’s gait intention is to be combined. Additionally, when a user wearing a hip exoskeleton robot walks, we will check whether the combined algorithm properly supports the muscle strength.