Angelo M. Sabatini

Quaternion-based extended Kalman filter for determining orientation by inertial and magnetic sensing

In this paper, a quaternion based extended Kalman filter (EKF) is developed for determining the orientation of a rigid body from the outputs of a sensor which is configured as the integration of a tri-axis gyro and an aiding system mechanized using a tri-axis accelerometer and a tri-axis magnetometer. The suggested applications are for studies in the field of human movement. In the proposed EKF, the quaternion associated with the body rotation is included in the state vector together with the bias of the aiding system sensors. Moreover, in addition to the in-line procedure of sensor bias compensation, the measurement noise covariance matrix is adapted, to guard against the effects which body motion and temporary magnetic disturbance may have on the reliability of measurements of gravity and earths magnetic field, respectively. By computer simulations and experimental validation with human hand orientation motion signals, improvements in the accuracy of orientation estimates are demonstrated for the proposed EKF, as compared with filter implementations where either the in-line calibration procedure, the adaptive mechanism for weighting the measurements of the aiding system sensors, or both are not implemented.

Assessment of walking features from foot inertial sensing

An ambulatory monitoring system is developed for the estimation of spatio-temporal gait parameters. The inertial measurement unit embedded in the system is composed of one biaxial accelerometer and one rate gyroscope, and it reconstructs the sagittal trajectory of a sensed point on the instep of the foot. A gait phase segmentation procedure is devised to determine temporal gait parameters, including stride time and relative stance; the procedure allows to define the time intervals needed for carrying an efficient implementation of the strapdown integration, which allows to estimate stride length, walking speed, and incline. The measurement accuracy of walking speed and inclines assessments is evaluated by experiments carried on adult healthy subjects walking on a motorized treadmill. Root-mean-square errors less than 0.18 km/h (speed) and 1.52% (incline) are obtained for tested speeds and inclines varying in the intervals [3, 6] km/h and [-5, +15]%, respectively. Based on the results of these experiments, it is concluded that foot inertial sensing is a promising tool for the reliable identification of subsequent gait cycles and the accurate assessment of walking speed and incline.

A Survey of Glove-Based Systems and Their Applications

Hand movement data acquisition is used in many engineering applications ranging from the analysis of gestures to the biomedical sciences. Glove-based systems represent one of the most important efforts aimed at acquiring hand movement data. While they have been around for over three decades, they keep attracting the interest of researchers from increasingly diverse fields. This paper surveys such glove systems and their applications. It also analyzes the characteristics of the devices, provides a road map of the evolution of the technology, and discusses limitations of current technology and trends at the frontiers of research. A foremost goal of this paper is to provide readers who are new to the area with a basis for understanding glove systems technology and how it can be applied, while offering specialists an updated picture of the breadth of applications in several engineering and biomedical sciences areas.

Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers

The use of on-body wearable sensors is widespread in several academic and industrial domains. Of great interest are their applications in ambulatory monitoring and pervasive computing systems; here, some quantitative analysis of human motion and its automatic classification are the main computational tasks to be pursued. In this paper, we discuss how human physical activity can be classified using on-body accelerometers, with a major emphasis devoted to the computational algorithms employed for this purpose. In particular, we motivate our current interest for classifiers based on Hidden Markov Models (HMMs). An example is illustrated and discussed by analysing a dataset of accelerometer time series.

Activity recognition using a single accelerometer placed at the wrist or ankle.

PURPOSE Large physical activity surveillance projects such as the UK Biobank and NHANES are using wrist-worn accelerometer-based activity monitors that collect raw data. The goal is to increase wear time by asking subjects to wear the monitors on the wrist instead of the hip, and then to use information in the raw signal to improve activity type and intensity estimation. The purposes of this work was to obtain an algorithm to process wrist and ankle raw data and to classify behavior into four broad activity classes: ambulation, cycling, sedentary, and other activities. METHODS Participants (N = 33) wearing accelerometers on the wrist and ankle performed 26 daily activities. The accelerometer data were collected, cleaned, and preprocessed to extract features that characterize 2-, 4-, and 12.8-s data windows. Feature vectors encoding information about frequency and intensity of motion extracted from analysis of the raw signal were used with a support vector machine classifier to identify a subjects activity. Results were compared with categories classified by a human observer. Algorithms were validated using a leave-one-subject-out strategy. The computational complexity of each processing step was also evaluated. RESULTS With 12.8-s windows, the proposed strategy showed high classification accuracies for ankle data (95.0%) that decreased to 84.7% for wrist data. Shorter (4 s) windows only minimally decreased performances of the algorithm on the wrist to 84.2%. CONCLUSIONS A classification algorithm using 13 features shows good classification into the four classes given the complexity of the activities in the original data set. The algorithm is computationally efficient and could be implemented in real time on mobile devices with only 4-s latency.

Estimating Three-Dimensional Orientation of Human Body Parts by Inertial/Magnetic Sensing

User-worn sensing units composed of inertial and magnetic sensors are becoming increasingly popular in various domains, including biomedical engineering, robotics, virtual reality, where they can also be applied for real-time tracking of the orientation of human body parts in the three-dimensional (3D) space. Although they are a promising choice as wearable sensors under many respects, the inertial and magnetic sensors currently in use offer measuring performance that are critical in order to achieve and maintain accurate 3D-orientation estimates, anytime and anywhere. This paper reviews the main sensor fusion and filtering techniques proposed for accurate inertial/magnetic orientation tracking of human body parts; it also gives useful recipes for their actual implementation.

A hybrid approach to EMG pattern analysis for classification of arm movements using statistical and fuzzy techniques

In this paper, a hybrid approach is presented for discriminating a few upper limb movements by processing the electromyographic (EMG) signals from selected shoulder muscles. Statistical techniques, such as the Generalized Likelihood Ratio test, the Principal Component Analysis, autoregressive parametric modeling techniques and cepstral analysis techniques, combined with a fuzzy logic based classifier (the Abe-Lan network) are used to construct low-dimensional feature spaces with high classification rates. The experimental results show the ability of the algorithm to correctly classify all the EMG patterns related to the selected planar arm pointing movements. Moreover, the structure presented offers promise for real-time applications because of the low computation costs of the overall algorithm.

Estimating orientation using magnetic and inertial sensors and different sensor fusion approaches: accuracy assessment in manual and locomotion tasks.

Magnetic and inertial measurement units are an emerging technology to obtain 3D orientation of body segments in human movement analysis. In this respect, sensor fusion is used to limit the drift errors resulting from the gyroscope data integration by exploiting accelerometer and magnetic aiding sensors. The present study aims at investigating the effectiveness of sensor fusion methods under different experimental conditions. Manual and locomotion tasks, differing in time duration, measurement volume, presence/absence of static phases, and out-of-plane movements, were performed by six subjects, and recorded by one unit located on the forearm or the lower trunk, respectively. Two sensor fusion methods, representative of the stochastic (Extended Kalman Filter) and complementary (Non-linear observer) filtering, were selected, and their accuracy was assessed in terms of attitude (pitch and roll angles) and heading (yaw angle) errors using stereophotogrammetric data as a reference. The sensor fusion approaches provided significantly more accurate results than gyroscope data integration. Accuracy improved mostly for heading and when the movement exhibited stationary phases, evenly distributed 3D rotations, it occurred in a small volume, and its duration was greater than approximately 20 s. These results were independent from the specific sensor fusion method used. Practice guidelines for improving the outcome accuracy are provided.

Quaternion-based strap-down integration method for applications of inertial sensing to gait analysis.

The proposed strap-down integration method exploits the cyclical nature of human gait: during the gait swing phase, the quaternion-based attitude representation is integrated using a gyroscope from initial conditions that are determined during stance by an accelerometer. Positioning requires double time integration of the gravity-compensated accelerometer signals during swing. An interpolation technique applied to attitude quaternions was developed to improve the accuracy of orientation and positioning estimates by accounting for the effect of sensor bias and scale factor drifts. A simulation environment was developed for the analysis and testing of the proposed algorithm on a synthetic movement trajectory. The aim was to define the true attitude and positioning used in the computation of estimation errors. By thermal modelling, the changes of bias and scale factor of the inertial sensors, calibrated at a single reference temperature, were analysed over a range of ±10°C, for measurement noise standard deviations up to σg = 2.5° s−1 (gyroscope) and σa = 0.05 m s−1 (accelerometer). The compensation technique reduced the maximum root mean square errors (RMSEs) to: RMSEθ=14.6° (orientation) and RMSEd=17.7 cm (positioning) for an integration interval of one gait cycle (an improvement of 3° and 7 cm); RMSEθ=14.8° and RMSEd=30.0 cm for an integration interval of two gait cycles (an improvement of 11° and 262 cm).

An algorithm for detecting the onset of muscle contraction by EMG signal processing

The Generalized Likelihood Ratio (GLR) test is proposed for estimating the time instant of muscle contraction onset via electromyographic (EMG) signal processing. In contrast to commonly used threshold-based estimation methods, the proposed algorithm proves to be reasonably accurate even for low levels of EMG activity; the improved behaviour of the GLR test comes with just a modest increase in the computational complexity. A set of computer simulation experiments are presented, where the proposed algorithm and two different threshold-based estimators are studied; also, we discuss the results of analysing the EMG recordings of selected proximal muscles of the upper limb in a hemiparetic subject.