The recognition of Activities of Daily Living (ADL) has been a widely debated topic, with applications in a vast range of fields. ADL recognition can be accomplished by processing data from wearable sensors, specially located at the lower trunk, which appears to be a suitable option in uncontrolled environments. Several authors have addressed ADL recognition using Artificial Intelligence (AI)-based algorithms, obtaining encouraging results. However, the number of ADL recognized by these algorithms is still limited, rarely focusing on transitional activities, and without addressing falls. Furthermore, the small amount of data used and the lack of information regarding validation processes are other drawbacks found in the literature. To overcome these drawbacks, a total of nine public and private datasets were merged in order to gather a large amount of data to improve the robustness of several ADL recognition algorithms. Furthermore, an AI-based framework was developed in this manuscript to perform a comparative analysis of several ADL Machine Learning (ML)-based classifiers. Feature selection algorithms were used to extract only the relevant features from the dataset’s lower trunk inertial data. For the recognition of 20 different ADL and falls, results have shown that the best performance was obtained with the K-NN classifier with the first 85 features ranked by Relief-F (98.22% accuracy). However, Ensemble Learning classifier with the first 65 features ranked by Principal Component Analysis (PCA) presented 96.53% overall accuracy while maintaining a lower classification time per window (0.039 ms), showing a higher potential for its usage in real-time scenarios in the future. Deep Learning algorithms were also tested. Despite its outcomes not being as good as in the prior procedure, their potential was also demonstrated (overall accuracy of 92.55% for Bidirectional Long Short-Term Memory (LSTM) Neural Network), indicating that they could be a valid option in the future.
Humans’ balance recovery responses to gait perturbations are negatively impacted with ageing. Slip and trip events, the main causes preceding falls during walking, are likely to produce severe injuries in older adults. While traditional exercise-based interventions produce inconsistent results in reducing patients’ fall rates, perturbation-based balance training (PBT) emerges as a promising task-specific solution towards fall prevention. PBT improves patients’ reactive stability and fall-resisting skills through the delivery of unexpected balance perturbations. The adopted perturbation conditions play an important role towards PBT’s effectiveness and the acquisition of meaningful sensor data for studying human biomechanical reactions to loss of balance (LOB) events. Hence, this narrative review aims to survey the different methods employed in the scientific literature to provoke artificial slips and trips in healthy adults during treadmill and overground walking. For each type of perturbation, a comprehensive analysis was conducted to identify trends regarding the most adopted perturbation methods, gait phase perturbed, gait speed, perturbed leg, and sensor systems used for data collection. The reliable application of artificial perturbations to mimic real-life LOB events may reduce the gap between laboratory and real-life falls and potentially lead to fall-rate reduction among the elderly community.
Ambient Assisted Living (AAL) represents a very relevant area of study since it is of great interest to monitor not only people in need of treatment or rehabilitatn, but also healthy and elderly people. One of the main necessities is to monitor the human gait. However, there are still some open issues to be addressed. Namely, literature shows that there are differences between indoor and outdoor environments. Thus, within the framework of a project to monitor human gait using IMUs (Inertial Measurement Units, MPU-6000 Motion Processing Units), the Enhanced Low Power Real Time (eLPRT) protocol was validated by obtaining the percentage of lost packets (lost protocol messages that contains inertial/magnetic sensors information). Concerning the system, the IMUs were connected to a base station (SmartRF05EB) by means of Radio Frequency (RF). This base station was connected to a personal computer to process the data in real time.In order to validate the communication protocol, the losses of data packets were accounted for during the trials carried out by one subject in three different environments: i) inside a laboratory; ii) in a corridor; and iii) in an outdoor environment. As results, the range of average percentage of loss was 0.52% to 15.21% inside the laboratory; 1.15% to 8.93% in the corridor; and 0.90% to 7.51% in the outdoor environment. The absence of ferromagnetic materials and other wireless communications with the same frequency band are the main reasons why the RF transmission had better results in an outdoor environment.
Recently, fall risk assessment has been a main focus in fall-related research. Wearable sensors have been used to increase the objectivity of this assessment, building on the traditional use of oversimplified questionnaires. However, it is necessary to define standard procedures that will us enable to acknowledge the multifactorial causes behind fall events while tackling the heterogeneity of the currently developed systems. Thus, it is necessary to identify the different specifications and demands of each fall risk assessment method. Hence, this manuscript provides a narrative review on the fall risk assessment methods performed in the scientific literature using wearable sensors. For each identified method, a comprehensive analysis has been carried out in order to find trends regarding the most used sensors and its characteristics, activities performed in the experimental protocol, and algorithms used to classify the fall risk. We also verified how studies performed the validation process of the developed fall risk assessment systems. The identification of trends for each fall risk assessment method would help researchers in the design of standard innovative solutions and enhance the reliability of this assessment towards a homogeneous benchmark solution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.