In this paper, a self-contained procedure to estimate the vertical, medial-lateral, and anterior-posterior displacement of a single sacrum-worn inertial measurement unit (IMU) is presented, which can be related to the human body center of mass (CoM) displacement during treadmill walking through an adaptation of the sacral marker method. Further, a magnetometer-free custom sensor-fusion algorithm for orientation estimation is proposed alongside a practical alignment procedure to refer relative IMU orientation estimation to a ground-fixed reference frame. Twelve healthy subjects performed two trials of treadmill walking at 3, 4 and 5 km/h for 150 s, with a sacrum-worn IMU. Orientation and displacement estimations were then compared with those obtained from an optoelectronic measurement system. Roll, pitch and yaw angles showed root mean square errors (RMSE) lower than 2 deg for walking trials at 3, 4 and 5 km/h, with Pearson’s correlation coefficient higher than 0.90 for each angle. Displacement accuracy was evaluated in terms of peak-to-trough distances and RMSE. Mean errors resulted lower than 1 mm for each axis of interest and for each gait speed, with RMSE not higher than 2.5 mm. The proposed off-line algorithm can be used in low-budget and infrastructure-free environments, to achieve reliable CoM displacement estimation during cyclic activities such as treadmill walking.

In this study, a minimal setup for the ankle joint kinematics estimation is proposed relying only on proximal information of the lower-limb, i.e. thigh muscles activity and joint kinematics. To this purpose, myoelectric activity of Rectus Femoris (RF), Biceps Femoris (BF), and Vastus Medialis (VM) were recorded by surface electromyography (sEMG) from six healthy subjects during unconstrained walking task. For each subject, the angular kinematics of hip and ankle joints were synchronously recorded with sEMG signal for a total of 288 gait cycles. Two feature sets were extracted from sEMG signals, i.e. time domain (TD) and wavelet (WT) and compared to have a compromise between the reliability and computational capacity, they were used for feeding three regression models, i.e. Artificial Neural Networks, Random Forest, and Least Squares - Support Vector Machine (LS-SVM). BF together with LS-SVM provided the best ankle angle estimation in both TD and WT domains (RMSE < 5.6 deg). The inclusion of Hip joint trajectory significantly enhanced the regression performances of the model (RMSE < 4.5 deg). Results showed the feasibility of estimating the ankle trajectory using only proximal and limited information from the lower limb which would maximize a potential transfemoral amputee user’s comfortability while facing the challenge of having a small amount of information thus requiring robust data-driven models. These findings represent a significant step towards the development of a minimal setup useful for the control design of ankle active prosthetics and rehabilitative solutions.

Muscle onset detection plays a key role in applications ranging from clinical to assistive technology. The Teager-Kaiser energy operator (TKEO) is an acknowledged tool used in surface electromyography (sEMG) signal conditioning for improving the performances of many change-point detection methods. Here, a TKEO extended version (ETKEO) was used to investigate its effects, for different SNR ranges, among a series of well-assessed algorithms, including a threshold-based one (TP). An optimization procedure on synthetic signals for the selection of the operator structure was also developed. The detection errors between TKEO and ETKEO, performed on real sEMG signals with SNR≤8 dB, showed significant (p<0.05) overall improvements, not lower than 30%, when ETKEO was used. When compared with more robust techniques preconditioned by ETKEO as well, i.e. wavelet-, CUSUM-and profile likelihood maximization-based algorithms, the TP detector reached comparable performances for each SNR band, also for the lowest one. The results support the relevance of using ETKEO to improve onset analysis methods for a wide range of low SNR values, being particularly suitable for applications such as myoelectric motion intention detection. Moreover, the ETKEO adaptable structure suggests its use for other biological signals, presenting different characteristics with respect to sEMG signals.

The analysis of gait rhythm by pattern recognition can support the state-of-the-art clinical methods for the identification of neurodegenerative diseases (NDD). In this study, we investigated the use of time domain (TD) and time-dependent spectral features (PSDTD) for detecting NDD sub-types. Also, we proposed two classification pathways for supporting NDD diagnosis, the first one made by a two-step learning phase, whereas the second one encompasses a single learning model. We considered stride-to-stride fluctuation data of healthy controls (CN), patients affected by Parkinson's disease (PD), Huntington's disease (HD), and amyotrophic lateral sclerosis (AS). TD feature set provided good results to distinguish between CN and NDDs, while performances lowered for specific NDD identification. PSDTD features boosted the accuracy of each binary identification task. With k -nearest neighbor classifier, the first diagnosis pathway reached 98.76% accuracy to distinguish between CN and NDD and 94.56% accuracy for NDDs sub-types, whereas the second pathway offered an overall accuracy of 94.84% for a 4-class classification task. Outcomes of this study indicate that the use of TD and PSDTD features, simple to extract and with a low computational load, provides reliable results in terms of NDD identification, being also useful for the development of gait rhythm computer-aided NDD detection systems.

Gait phase recognition systems based on surface electromyographic signals (EMGs) are crucial for developing advanced myoelectric control schemes that enhance the interaction between humans and lower limb assistive devices. However, machine learning models used in this context, such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), typically experience performance degradation when modeling the gait cycle with more than just stance and swing phases. This study introduces a generalized phasor-based feature extraction approach (PHASOR) that captures spatial myoelectric features to improve the performance of LDA and SVM in gait phase recognition. A publicly available dataset of 40 subjects was used to evaluate PHASOR against state-of-the-art feature sets in a five-phase gait recognition problem. Additionally, fully data-driven deep learning architectures, such as Rocket and Mini-Rocket, were included for comparison. The separability index (SI) and mean semi-principal axis (MSA) analyses showed mean SI and MSA metrics of 7.7 and 0.5, respectively, indicating the proposed approach’s ability to effectively decode gait phases through EMG activity. The SVM classifier demonstrated the highest accuracy of 82% using a five-fold leave-one-trial-out testing approach, outperforming Rocket and Mini-Rocket. This study confirms that in gait phase recognition based on EMG signals, novel and efficient muscle synergy information feature extraction schemes, such as PHASOR, can compete with deep learning approaches that require greater processing time for feature extraction and classification.