Wearable step counting using a force myography-based ankle strap

Predicting vertical ground reaction forces from 3D accelerometry using reservoir computers leads to accurate gait event detection

Accelerometers are low-cost measurement devices that can readily be used outside the lab. However, determining isolated gait events from accelerometer signals, especially foot-off events during running, is an open problem. We outline a two-step approach where machine learning serves to predict vertical ground reaction forces from accelerometer signals, followed by force-based event detection. We collected shank accelerometer signals and ground reaction forces from 21 adults during comfortable walking and running on an instrumented treadmill. We trained one common reservoir computer using segmented data using both walking and running data. Despite being trained on just a small number of strides, this reservoir computer predicted vertical ground reaction forces in continuous gait with high quality. The subsequent foot contact and foot off event detection proved highly accurate when compared to the gold standard based on co-registered ground reaction forces. Our proof-of-concept illustrates the capacity of combining accelerometry with machine learning for detecting isolated gait events irrespective of mode of locomotion.

A Review of EMG-, FMG-, and EIT-Based Biosensors and Relevant Human–Machine Interactivities and Biomedical Applications

Wearables developed for human body signal detection receive increasing attention in the current decade. Compared to implantable sensors, wearables are more focused on body motion detection, which can support human–machine interaction (HMI) and biomedical applications. In wearables, electromyography (EMG)-, force myography (FMG)-, and electrical impedance tomography (EIT)-based body information monitoring technologies are broadly presented. In the literature, all of them have been adopted for many similar application scenarios, which easily confuses researchers when they start to explore the area. Hence, in this article, we review the three technologies in detail, from basics including working principles, device architectures, interpretation algorithms, application examples, merits and drawbacks, to state-of-the-art works, challenges remaining to be solved and the outlook of the field. We believe the content in this paper could help readers create a whole image of designing and applying the three technologies in relevant scenarios.

Building Effective Machine Learning Models for Ankle Joint Power Estimation During Walking Using FMG Sensors

Ankle joint power is usually determined by a complex process that involves heavy equipment and complex biomechanical models. Instead of using heavy equipment, we proposed effective machine learning (ML) and deep learning (DL) models to estimate the ankle joint power using force myography (FMG) sensors. In this study, FMG signals were collected from nine young, healthy participants. The task was to walk on a special treadmill for five different velocities with a respective duration of 1 min. FMG signals were collected from an FMG strap that consists of 8 force resisting sensor (FSR) sensors. The strap was positioned around the lower leg. The ground truth value for ankle joint power was determined with the help of a complex biomechanical model. At first, the predictors' value was preprocessed using a rolling mean filter. Following, three sets of features were formed where the first set includes raw FMG signals, and the other two sets contained time-domain and frequency-domain features extracted using the first set. Cat Boost Regressor (CBR), Long-Short Term Memory (LSTM), and Convolutional Neural Network (CNN) were trained and tested using these three features sets. The results presented in this study showed a correlation coefficient of R = 0.91 ± 0.07 for intrasubject testing and were found acceptable when compared to other similar studies. The CNN on raw features and the LSTM on time-domain features outperformed the other variations. Aside from that, a performance gap between the slowest and fastest walking distance was observed. The results from this study showed that it was possible to achieve an acceptable correlation coefficient in the prediction of ankle joint power using FMG sensors with an appropriate combination of feature set and ML model.

A standalone computing system to classify human foot movements using machine learning techniques for ankle-foot prosthesis control

This paper presents different machine learning techniques to classify the following foot movements: (i) dorsiflexion, (ii) plantarflexion, (iii) inversion, (iv) eversion, (v) medial rotation, and (vi) lateral rotation. The purpose is to design a real-time standalone computing system to predict the foot movements in the sagittal plane, useful for ankle-foot prosthesis control. Electromyography (EMG) and forcemyography (FMG) signals were acquired from the leg's tibialis anterior, medial gastrocnemius, lateral gastrocnemius, and peroneus longus muscles. First, Raspberry Pi was used to acquire EMG/FMG signals and to classify foot movements in real-time using different machine learning techniques. Later, an Arduino Nano 33 BLE controller was employed to implement the TinyML algorithm to classify these foot movements in the Arduino environment. The results showed that Raspberry Pi-based classification provided more than 99.5% accuracy for the EMG signals using LDA, LR, KNN, and SVC classifiers for offline prediction. However, for the classification of real-time signals, the performance of LDA is exceptionally well in predicting all classes. For Arduino Nano 33 BLE controller, the TinyML algorithm performed the classification task in real-time (8.5msec) without any misclassification. Further, the classification accuracy using EMG signal is much better than FMG based classification. Finally, the TinyML algorithm is applied on a transtibial amputee, and it is found that all three classes were classified correctly. Our finding suggests that a TinyML based Arduino Nano 33 BLE microcontroller is comparatively faster to predict and control, and it is smaller in size, thus advantageous for real-time prosthetic leg control applications.

Optimal Force Myography Placement For Maximizing Locomotion Classification Accuracy in Transfemoral Amputees: A Pilot Study

Force myography (FMG), is shown to be a promising alternative to electromyography in locomotion classification. However, the placement of force myography sensors over the thigh during locomotion is not yet clear. To this end, an inhouse developed FMG strap was placed over the thigh muscles of healthy/amputees, while walking on different terrains. The performance of the system was tested on six healthy and two amputees during the five different placements of FMG strap i.e., base, distal, lateral, medial, and proximal. The study reveals that there is an increase in average accuracy (STD) from [mean (STD)] 96.4% (4.0) to 99.5% (0.5) for healthy individuals and 95.5% (3.0) to 99.1% (0.3) for amputees while moving the FMG strap to the proximal of the thigh/stump. The study further determines the combination of three FMG channels on anterior side (Rectus Femoris, Vastus lateralis, and Iliotibial Tract muscles) that provides classification accuracy at par (p > 0.05) to utilizing all eight channels for locomotion classification. The variation of humidity throughout the trials did not significantly (p > 0.05) affect the classification accuracy. The study concludes that the optimal location to place the FMG strap is proximal to the thigh/ stump with a minimum of three FMG channels on the anterior part of the thigh for superior classification accuracy.

A New Force Myography-Based Approach for Continuous Estimation of Knee Joint Angle in Lower Limb Amputees and Able-Bodied Subjects

In this paper, we present a new method for estimating knee joint angle using force myography. The technique utilized force myogram signals from thigh muscles while subjects walked on a treadmill at different speeds, i.e., slow, medium, fast, and run. An eight-channel in-house force myography (FMG) data acquisition system was developed to collect the data wirelessly from seven healthy subjects and a transfemoral amputee. An artificial neural network was employed to estimate the knee joint angle from force myogram signals. The root-mean-square error across the healthy subjects was 6.9±1.5° at slow (1.5 km/hr), 6.5±1.3° at medium (4 km/hr), 7.4±2.2° at fast (6 km/hr) speeds, and 8.1±2.2° while running (8 km/hr). The root-mean-square error, across the trials, for the transfemoral amputee was 4.0±1.2° at slow (1 km/hr), 3.2±0.6° at medium (2 km/hr) and 3.8±0.9° at fast (3 km/hr) speeds. The proposed approach is useful in real-time gait analysis. The system is easily wearable, convenient in out-door use, portable, and commercially viable.

Person Re-Identification Using Deep Modeling of Temporally Correlated Inertial Motion Patterns

Person re-identification (re-ID) is among the essential components that play an integral role in constituting an automated surveillance environment. Majorly, the problem is tackled using data acquired from vision sensors using appearance-based features, which are strongly dependent on visual cues such as color, texture, etc., consequently limiting the precise re-identification of an individual. To overcome such strong dependence on visual features, many researchers have tackled the re-identification problem using human gait, which is believed to be unique and provide a distinctive biometric signature that is particularly suitable for re-ID in uncontrolled environments. However, image-based gait analysis often fails to extract quality measurements of an individual’s motion patterns owing to problems related to variations in viewpoint, illumination (daylight), clothing, worn accessories, etc. To this end, in contrast to relying on image-based motion measurement, this paper demonstrates the potential to re-identify an individual using inertial measurements units (IMU) based on two common sensors, namely gyroscope and accelerometer. The experiment was carried out over data acquired using smartphones and wearable IMUs from a total of 86 randomly selected individuals including 49 males and 37 females between the ages of 17 and 72 years. The data signals were first segmented into single steps and strides, which were separately fed to train a sequential deep recurrent neural network to capture implicit arbitrary long-term temporal dependencies. The experimental setup was devised in a fashion to train the network on all the subjects using data related to half of the step and stride sequences only while the inference was performed on the remaining half for the purpose of re-identification. The obtained experimental results demonstrate the potential to reliably and accurately re-identify an individual based on one’s inertial sensor data.

A Wearable Gait Phase Detection System Based on Force Myography Techniques

(1) Background: Quantitative evaluation of gait parameters can provide useful information for constructing individuals’ gait profile, diagnosing gait abnormalities, and better planning of rehabilitation schemes to restore normal gait pattern. Objective determination of gait phases in a gait cycle is a key requirement in gait analysis applications; (2) Methods: In this study, the feasibility of using a force myography-based technique for a wearable gait phase detection system is explored. In this regard, a force myography band is developed and tested with nine participants walking on a treadmill. The collected force myography data are first examined sample-by-sample and classified into four phases using Linear Discriminant Analysis. The gait phase events are then detected from these classified samples using a set of supervisory rules; (3) Results: The results show that the force myography band can correctly detect more than 99.9% of gait phases with zero insertions and only four deletions over 12,965 gait phase segments. The average temporal error of gait phase detection is 55.2 ms, which translates into 2.1% error with respect to the corresponding labelled stride duration; (4) Conclusions: This proof-of-concept study demonstrates the feasibility of force myography techniques as viable solutions in developing wearable gait phase detection systems.