Deep neural network (DNN) models have become highly effective tools for function estimation in regression tasks, with applications in various domains, including human gait stride length estimation. ...Several studies have developed DNN models that use gait cycle data from wearable devices equipped with inertial measurement units to accurately predict stride lengths within a cycle. However, many of these deep learning approaches do not quantify predictive uncertainty and fail to consider individual gait characteristics. To address these limitations, we introduced an ensemble model based on a heteroscedastic neural network that quantifies the uncertainty in stride length predictions. Additionally, we proposed a novel stride training strategy that uses the average stride instead of individual strides to optimize the training process and improve model efficiency. Our extensive performance evaluations demonstrate the robustness and adaptability of our model, accurately predicting both the uncertainty of individual stride lengths and the specific stride lengths for each gait cycle. Our study represents a significant advancement in stride length estimation, addressing the challenges of uncertainty quantification and capturing the unique aspects of human gait. The proposed model has considerable potential for practical applications in gait analysis and related fields.
•A Heteroscedastic Neural Network for stride length prediction with uncertainty.•A novel training approach that focuses on an individual’s average stride length.•Estimation of each stride length and the overall distribution.•Rigorous separation of data at the object level for evaluation purposes.
Inertial motion analysis is having a growing interest during the last decades due to its advantages over classical optical systems. The technological solution based on inertial measurement units ...allows the measurement of movements in daily living environments, such as in everyday life, which is key for a realistic assessment and understanding of movements. This is why research in this field is still developing and different approaches are proposed. This presents a systematic review of the different proposals for inertial motion analysis found in the literature. The search strategy has been carried out in eight different platforms, including journal articles and conference proceedings, which are written in English and published until August 2022. The results are analyzed in terms of the publishers, the sensors used, the applications, the monitored units, the algorithms of use, the participants of the studies and the validation systems employed. In addition, we delve deeply into the machine learning techniques proposed in recent years and in the approaches to reduce the estimation error. In this way, we show an overview of the research carried out in this field, going into more detail in recent years, and providing some research directions for future work.
The increasing interest in assessing physical demands in team sports has led to the development of multiple sports related monitoring systems. Due to technical limitations, these systems primarily ...could be applied to outdoor sports, whereas an equivalent indoor locomotion analysis is not established yet. Technological development of inertial measurement units (IMU) broadens the possibilities for player monitoring and enables the quantification of locomotor movements in indoor environments. The aim of the current study was to validate an IMU measuring by determining average and peak human acceleration under indoor conditions in team sport specific movements. Data of a single wearable tracking device including an IMU (Optimeye S5, Catapult Sports, Melbourne, Australia) were compared to the results of a 3D motion analysis (MA) system (Vicon Motion Systems, Oxford, UK) during selected standardized movement simulations in an indoor laboratory (
= 56). A low-pass filtering method for gravity correction (LF) and two sensor fusion algorithms for orientation estimation Complementary Filter (CF), Kalman-Filter (KF) were implemented and compared with MA system data. Significant differences (
< 0.05) were found between LF and MA data but not between sensor fusion algorithms and MA. Higher precision and lower relative errors were found for CF (RMSE = 0.05; CV = 2.6%) and KF (RMSE = 0.15; CV = 3.8%) both compared to the LF method (RMSE = 1.14; CV = 47.6%) regarding the magnitude of the resulting vector and strongly emphasize the implementation of orientation estimation to accurately describe human acceleration. Comparing both sensor fusion algorithms, CF revealed slightly lower errors than KF and additionally provided valuable information about positive and negative acceleration values in all three movement planes with moderate to good validity (CV = 3.9 - 17.8%). Compared to x- and y-axis superior results were found for the z-axis. These findings demonstrate that IMU-based wearable tracking devices can successfully be applied for athlete monitoring in indoor team sports and provide potential to accurately quantify accelerations and decelerations in all three orthogonal axes with acceptable validity. An increase in accuracy taking magnetometers in account should be specifically pursued by future research.
Inertial navigation systems (INSs) are a topical solution in underwater navigation. Although appealing due to their ability to estimate pose without external information, INS suffer from compounding ...position errors due to bias and random noise. In general, INSs require the assistance of other positioning devices to achieve satisfactory positioning results. To solve these problems, this article proposes an ego-motion estimation framework with an inertial measurement unit (IMU) and magnetic compass based on the deep learning theory. The main idea is to estimate the displacement of vehicles from the IMU data in the time window and combine this with magnetic compass headings to reconstruct the trajectories of the vehicles. The preintegration technology is used to process raw IMU data, which mathematically separates the dependence of traditional inertial algorithms based on the initial value. Then, convolutional neural networks (CNNs) and attention hybrid networks are used to estimate the displacement of vehicles. In addition, the framework leverages the backpropagation neural network (BPNN) to fuse the magnetic heading and IMU measurements to obtain an accurate heading. Compared with other deep learning methods, the proposed method reduces computational complexity and improves position accuracy. Eventually, the accuracy of the proposed method is verified in the sea trail. The results show that the maximum value of absolute trajectory errors accounts for 12.8% of the distance in severe sea conditions and 6.38% in usual sea conditions.
This paper presents the development and testing of a novel electronic device for Wireless Motion Capture (W-MoCap), a technology that allows the reconstruction of movements of objects and body parts ...with many potential applications in various contexts. The device integrates UHF RFID technology with sensors for low-power backscattering communication. It consists of a Battery Assisted Passive UHF RFID chip, an Inertial Measurement Unit, an ultra-low power microcontroller, and a custom-designed edge-fed body-tolerant antenna operating at 866 MHz. The proper matching between the RFID chip and antenna is ensured through a well-designed L-match unbalanced network, and the separation of RF and DC signals is achieved with a meandered microstrip quarter-wavelength transformer, choke inductor, and decoupling capacitor. The designed and realized RFID W-MoCap Sensor-Tag has been thoroughly evaluated in terms of current consumption, front-end sensitivity, and sensing accuracy. Finally, five prototypes have been applied to specific segments of a human subject and successfully tested in a practical scenario for real time reconstruction of human movements.
The aim of this study was to investigate the reliability and concurrent validity of a commercially available Xsens MVN BIOMECH inertial-sensor-based motion capture system during clinically relevant ...functional activities. A clinician with no prior experience of motion capture technologies and an experienced clinical movement scientist each assessed 26 healthy participants within each of two sessions using a camera-based motion capture system and the MVN BIOMECH system. Participants performed overground walking, squatting, and jumping. Sessions were separated by 4 ± 3 days. Reliability was evaluated using intraclass correlation coefficient and standard error of measurement, and validity was evaluated using the coefficient of multiple correlation and the linear fit method. Day-to-day reliability was generally fair-to-excellent in all three planes for hip, knee, and ankle joint angles in all three tasks. Within-day (between-rater) reliability was fair-to-excellent in all three planes during walking and squatting, and poor-to-high during jumping. Validity was excellent in the sagittal plane for hip, knee, and ankle joint angles in all three tasks and acceptable in frontal and transverse planes in squat and jump activity across joints. Our results suggest that the MVN BIOMECH system can be used by a clinician to quantify lower-limb joint angles in clinically relevant movements.
Pérez-Castilla, A, Piepoli, A, Delgado-García, G, Garrido-Blanca, G, and García-Ramos, A. Reliability and concurrent validity of seven commercially available devices for the assessment of movement ...velocity at different intensities during the bench press. J Strength Cond Res 33(5): 1258-1265, 2019-The aim of this study was to compare the reliability and validity of 7 commercially available devices to measure movement velocity during the bench press exercise. Fourteen men completed 2 testing sessions. One-repetition maximum (1RM) in the bench press exercise was determined in the first session. The second testing session consisted of performing 3 repetitions against 5 loads (45, 55, 65, 75, and 85% of 1RM). The mean velocity was simultaneously measured using an optical motion sensing system (Trio-OptiTrack; "gold-standard") and 7 commercially available devices: 1 linear velocity transducer (T-Force), 2 linear position transducers (Chronojump and Speed4Lift), 1 camera-based optoelectronic system (Velowin), 1 smartphone application (PowerLift), and 2 inertial measurement units (IMUs) (PUSH band and Beast sensor). The devices were ranked from the most to the least reliable as follows: (a) Speed4Lift (coefficient of variation CV = 2.61%); (b) Velowin (CV = 3.99%), PowerLift (3.97%), Trio-OptiTrack (CV = 4.04%), T-Force (CV = 4.35%), and Chronojump (CV = 4.53%); (c) PUSH band (CV = 9.34%); and (d) Beast sensor (CV = 35.0%). A practically perfect association between the Trio-OptiTrack system and the different devices was observed (Pearson's product-moment correlation coefficient (r) range = 0.947-0.995; p < 0.001) with the only exception of the Beast sensor (r = 0.765; p < 0.001). These results suggest that linear velocity/position transducers, camera-based optoelectronic systems, and the smartphone application could be used to obtain accurate velocity measurements for restricted linear movements, whereas the IMUs used in this study were less reliable and valid.
Elderly patients often have more than one disease that affects walking behavior. An objective tool to identify which disease is the main cause of functional limitations may aid clinical decision ...making. Therefore, we investigated whether gait patterns could be used to identify degenerative diseases using machine learning. Data were extracted from a clinical database that included sagittal joint angles and spatiotemporal parameters measured using seven inertial sensors, and anthropometric data of patients with unilateral knee or hip osteoarthritis, lumbar or cervical spinal stenosis, and healthy controls. Various classification models were explored using the MATLAB Classification Learner app, and the optimizable Support Vector Machine was chosen as the best performing model. The accuracy of discrimination between healthy and pathologic gait was 82.3%, indicating that it is possible to distinguish pathological from healthy gait. The accuracy of discrimination between the different degenerative diseases was 51.4%, indicating the similarities in gait patterns between diseases need to be further explored. Overall, the differences between pathologic and healthy gait are distinct enough to classify using a classical machine learning model; however, routinely recorded gait characteristics and anthropometric data are not sufficient for successful discrimination of the degenerative diseases.
In the last few years, estimating ground reaction forces by means of wearable sensors has come to be a challenging research topic paving the way to kinetic analysis and sport performance testing ...outside of labs. One possible approach involves estimating the ground reaction forces from kinematic data obtained by inertial measurement units (IMUs) worn by the subject. As estimating kinetic quantities from kinematic data is not an easy task, several models and protocols have been developed over the years. Non-wearable sensors, such as optoelectronic systems along with force platforms, remain the most accurate systems to record motion. In this review, we identified, selected and categorized the methodologies for estimating the ground reaction forces from IMUs as proposed across the years. Scopus, Google Scholar, IEEE Xplore, and PubMed databases were interrogated on the topic of Ground Reaction Forces estimation based on kinematic data obtained by IMUs. The identified papers were classified according to the methodology proposed: (i) methods based on direct modelling; (ii) methods based on machine learning. The methods based on direct modelling were further classified according to the task studied (walking, running, jumping, etc.). Finally, we comparatively examined the methods in order to identify the most reliable approaches for the implementation of a ground reaction force estimator based on IMU data.