The Timed-Up and Go test is a simple yet effective test used to evaluate balance and mobility in conditions that affect movement, such as Parkinson’s disease. This test can inform clinicians about the monitoring and progression of the disease by measuring the time taken to complete the test. We used a smartphone app to obtain the phone’s inertial data and implemented an algorithm to automatically extract the time taken to complete the test. We considered data collected from six healthy participants performing tests at different speeds. The proposed method was further tested on twelve participants with Parkinson’s disease based on a reference measurement in clinic. We show that, for both groups, we obtain good accuracy (RMSE = 3.42 and 1.95 s) and a strong positive correlation (r = 0.85 and 0.83) between estimated duration and ground truth. We highlight limitations in our approach when the test is performed at very low speed or without a clear pause between the test and the user interaction with the phone. 

This paper addresses the need for accurate and continuous measurement of walked distance in applications such as indoor localisation, gait analysis or the 6-minute walk test (6MWT). We propose a method to continuously collect ground truth data of walked distance using an IoT-based trundle wheel. The wheel is connected via Bluetooth Low Energy to a smartphone application which allows the collection of inertial sensor data and GPS location information in addition to the reference distance. We prove the usefulness of this data collection approach in a use case where we derive walked distance from inertial data. We train a 1-dimensional CNN on inertial data collected by one researcher in 15 walking sessions of 1 km length at varying speeds. The training is facilitated by the continuous nature of the reference data. The accuracy of the algorithm is then tested on holdout data of a 6-min duration for which the error of the inferred distance is within clinically significant limits. The proposed approach is useful for the efficient collection of input and reference data for the development of algorithms used to estimate walked distance, such as for the 6MWT. 

As a result of technological advancements, functional capacity assessments, such as the 6-minute walk test, can be performed remotely, at home and in the community. Current studies, however, tend to overlook the crucial aspect of data quality, often limiting their focus to idealised scenarios. Challenging conditions may arise when performing a test given the risk of collecting poor-quality GNSS signal, which can undermine the reliability of the results. This work shows the impact of applying filtering rules to avoid noisy samples in common algorithms that compute the walked distance from positioning data. Then, based on signal features, we assess the reliability of the distance estimation using logistic regression from the following two perspectives: error-based analysis, which relates to the estimated distance error, and user-based analysis, which distinguishes conventional from unconventional tests based on users' previous annotations. We highlight the impact of features associated with walked path irregularity and direction changes to establish data quality. We evaluate features within a binary classification task and reach an F1-score of 0.93 and an area under the curve of 0.97 for the user-based classification. Identifying unreliable tests is helpful to clinicians, who receive the recorded test results accompanied by quality assessments, and to patients, who can be given the opportunity to repeat tests classified as not following the instructions.

Tracking a person’s activities is relevant in a variety of contexts, from health and group-specific assessments, such as elderly care, to fitness tracking and human–computer interaction. In a clinical context, sensor-based activity tracking could help monitor patients’ progress or deterioration during their hospitalization time. However, during routine hospital care, devices could face displacements in their position and orientation caused by incorrect device application, patients’ physical peculiarities, or patients’ day-to-day free movement. These aspects can significantly reduce algorithms’ performances. In this work, we investigated how shifts in orientation could impact Human Activity Recognition (HAR) classification. To reach this purpose, we propose an HAR model based on a single three-axis accelerometer that can be located anywhere on the participant’s trunk, capable of recognizing activities from multiple movement patterns, and, thanks to data augmentation, can deal with device displacement. Developed models were trained and validated using acceleration measurements acquired in fifteen participants, and tested on twenty-four participants, of which twenty were from a different study protocol for external validation. The obtained results highlight the impact of changes in device orientation on a HAR algorithm and the potential of simple wearable sensor data augmentation for tackling this challenge. When applying small rotations (<20 degrees), the error of the baseline non-augmented model steeply increased. On the contrary, even when considering rotations ranging from 0 to 180 along the frontal axis, our model reached a f1-score of 0.85±0.110.85±0.11 against a baseline model f1-score equal to 0.49±0.120.49±0.12.