In this paper we present a wearable high rate MIMU (magneticinertial measurement unit) based body tracking system. It is designed using low cost state-of-art hardware and MEMS sensors to reduce errors and improve computational latency. Our system allows for high rate data acquisition and sensor fusion at low power budget. It can be used for range of applications from extreme activity capture and biomechanical analysis to clinical evaluation and ambulatory health monitoring/rehabilitation. The package size of sensing nodes is small, and we use textile wires which make it very flexible. Thus entire system can be easily integrated with body worn suit/pants. Up to 7x nodes can be connected without compromising the maximum sampling frequency (1 KHz), with the possibility to add more nodes using additional bridge stations between nodes. The acquisition rate can be preset from 1 KHz to 100 Hz to suit the application or accuracy requirements. To the best of our knowledge, our inertial motion capture system is the first to offer such high rate output at 1 KHz for multiple nodes. The high rate of inertial data provides intrinsic accuracy to sensor fusion as well as capture high frequency features for clinical diagnostics and biomechanical analysis in ambient settings. The system also runs an embedded sensor fusion algorithm for accurate orientation estimation. We introduce a novel accelerometer and magnetometer measurement correction with adaptive sensor covariance approach in EKF, which makes it robust to both magnetic disturbances and body accelerations. Thus it is well suited for indoor human motion analysis and monitoring highly dynamic motion.

We propose a deep learning based framework that learns data-driven temporal priors to perform 3D human pose estimation from six body worn Magnetic Inertial Measurement units sensors. Our work estimates 3D human pose with associated uncertainty from sparse body worn sensors. We derive and implement a 3D angle representation that eliminates yaw angle (or magnetometer dependence) and show that 3D human pose is still obtained from this reduced representation, but with enhanced uncertainty. We do not use kinematic acceleration as input and show that it improves the generalization to real sensor data from different subjects as well as accuracy. Our framework is based on Bi-directional recurrent autoencoder. A sliding window is used at inference time, instead of full sequence (offline mode). The major contribution of our research is that 3D human pose is predicted from sparse sensors with a well calibrated uncertainty which is correlated with ambiguity and actual errors. We have demonstrated our results on two real sensor datasets; DIP-IMU and Total capture and have come up with state-of-art accuracy. Our work confirms that the main limitation of sparse sensor based 3D human pose prediction is the lack of temporal priors. Therefore fine-tuning on a small synthetic training set of target domain, improves the accuracy.

The ambulatory motion capture and gait analysis using wearable MEMS based magnetic-inertial measurement units (MIMUs) is challenging despite multisensor fusion and effective anatomical (sensor-to-segment) calibration. The MEMS based sensors show degraded performance when run for long time, especially indoors. This is due to the fact that assumption of no acceleration except gravity and homogenous magnetic field no longer holds, when the motion is being performed. The rate gyro is used to complement the accelerometer/ magnetometer for orientation estimation, but integration of its residual biases as well as noise eventually causes the sensor fusion estimates to drift. The errors in heading angle or yaw are particular significant due to persistent nature of magnetic inhomogeneity in the environment. This ultimately results in inaccurate and drifting joint angle estimates between body segments that would require some means of correction. In present work, we propose a new adaptive covariance based EKF for sensor fusion which makes it effectively robust to both dynamic body accelerations as well as inhomogeneous magnetic field. The adaptive covariance method penalizes the bad accelerometer and magnetometer measurements and intelligently updates the gyro biases online using only undisturbed readings of accelerometer/magnetometer. Our sensor fusion algorithm provides accurate orientation estimates for each MIMU node over time. In order to account for any residual drift of joint angles, we propose a novel correction term in our anatomical formulation that performs online correction of drift in individual joint angles and updates it as an orientation offset. This offset correction for joint angle is performed automatically when the limb or extended torso are in neutral quasi-static pose and this condition is judged using accelerometers. Overall our approach achieves precise orientation estimates in highly dynamic conditions and avoids drift or error accumulation due to inhomogeneous magnetic fields during inertial motion capture.

Privacy and Data protection are highly complex issues within eHealth/M-Health systems. These systems should meet specific requirements deriving from the organizations and users, as well as from the variety of legal obligations deriving from GDPR that dictate protection rights of data subjects and responsibilities of data controllers. To address that, this paper proposes a Privacy and Data Protection Framework that provides the appropriate steps so as the proper technical, organizational and procedural measures to be undertaken. The framework, beyond previous literature, supports the combination of privacy by design principles with the newly introduced GDPR requirements in order to create a strong elicitation process for deriving the set of the technical security and privacy requirements that should be addressed. It also proposes a process for validating that the elicited requirements are indeed fulfilling the objectives addressed during the Data Protection Impact Assessment (DPIA), carried out according to the GDPR.

A fast method to simultaneously calibrate multiple MEMS Magnetic Inertial Measurement Units (MIMUs) accurately in the field is needed in many application areas. The MEMS MIMUs require calibration of systematic errors of bias, sensitivity, non-orthogonality and misalignment, which vary with temperature and use. Even after calibration, the sensors undergo stochastic errors in static and dynamic conditions and thus uncertainty of output must also be modeled. We propose a method for easy and fast calibration of multiple MIMUs together, while mounted on a single platform. The precise alignment of sensors is not assumed. Our method calibrates both fixed array of MEMS MIMUs or many independent MIMUs simultaneously using kinematic constraints. The novelty of our approach is that the uncertainty of sensors output is also learned as part of our model. Compared with existing state-of-art methods, our algorithm gives more consistent readings of all MIMUs and our framework also predicts the associated uncertainty of the sensor output. The uncertainty prediction of individual sensors is particularly helpful in the sensor fusion.