Now that wearable sensors have become more commonplace, it is possible to monitor individual healthcare-related activity outside the clinic, unleashing potential for early detection of events in diseases such as Parkinson’s disease (PD). However, the unsupervised and “open world” nature of this type of data collection make such applications difficult to develop. In this proof-of-concept study, we used inertial sensor data from Verily Study Watches worn by individuals for up to 23 h per day over several months to distinguish between seven subjects with PD and four without. Since motor-related PD symptoms such as bradykinesia and gait abnormalities typically present when a PD subject is walking, we initially used human activity recognition (HAR) techniques to identify walk-like activity in the unconstrained, unlabeled data. We then used these “walk-like” events to train one-dimensional convolutional neural networks (1D-CNNs) to determine the presence of PD. We report classification accuracies near 90% on single 5-s walk-like events and 100% accuracy when taking the majority vote over single-event classifications that span a duration of one day. Though based on a small cohort, this study shows the feasibility of leveraging unconstrained wearable sensor data to accurately detect the presence or absence of PD.

The non-invasive nature of near-infrared spectroscopy (NIRS) makes it a widely accepted method for blood oxygenation measurement in various parts of the human body. One of the main challenges in this method lies in the successful removal of movement artefacts in the detected signal. In this respect, multi-channel inertia measurement unit (IMU) containing accelerometer, gyroscope and magnetometer can be used for better modelling of movement artefact than using accelerometer only, which as a result, movement artefact can be more accurately removed. A wearable two-channel continuous wave NIRS system, incorporating an IMU sensor which contain accelerometer, gyroscope and magnetometer in it, was developed to record NIRS signal along with the simultaneous recording of movement artefacts related signal using the IMU. Four healthy subjects volunteered in the recording of the NIRS signals. During the recording from the first two subject, movement artefacts were simulated in one of the NIRS channels by tapping the photodiode sensor nearby. The corresponding IMU data for the simulated movement artefacts were used to estimate the artefacts in the corrupted signal by autoregressive with exogenous input method and subtracted from the corrupted signal to remove the artefacts in the NIRS signal. Signal-to-noise ratio (SNR) improvement was used to evaluate the performance of the movement artefacts removal process. The performance of the movement artefacts estimation and removal were compared using accelerometer only, accelerometer and gyroscope, and accelerometer, gyroscope and magnetometer data from IMU sensor to estimate the artefact in NIRS reading. For the remaining two subjects the NIRS signal was recorded by natural movement artefacts impact and the results of artefacts removal was compared using accelerometer only, accelerometer and gyroscope, and accelerometer, gyroscope and magnetometer data from IMU sensor to estimate the artefact in NIRS reading. The quantitative and qualitative results revealed that the SNR improvement increases with the number of IMU channels used in the artefacts estimation, and there were approximately 5–11 dB increase in SNR when nine channel IMU data were used rather than using only three channel accelerometer data only. The artefact removal from natural movements also demonstrated that the combination of gyroscope and magnetometer sensors with accelerometer provided better estimation and removal of the movement artefacts, which was revealed by the minimal change of the HbO2 and Hb level before, during and after movement artefacts occurred in the NIRS signal. The movement artefacts in NIRS can be more accurately estimated and removed by using accelerometer, gyroscope and magnetograph signals from an integrated IMU sensor than using accelerometer signal only.

Functional Near-Infrared Spectroscopy (fNIRS) is a hemodynamic modality in human cognitive workload assessment receiving popularity due to its easier implementation, non-invasiveness, low cost and other benefits from the signal-processing point of view. Wearable wireless fNIRS systems used in research have promisingly shown that fNIRS could be used in cognitive workload assessment in out-of-the-lab scenarios, such as in operators’ cognitive workload monitoring. In such a scenario, the wearability of the system is a significant factor affecting user comfort. In this respect, the wearability of the system can be improved if it is possible to minimize an fNIRS system without much compromise of the cognitive workload detection accuracy. In this study, cognitive workload-related hemodynamic changes were acquired using an fNIRS system covering the whole forehead, which is the region of interest in most cognitive workload-monitoring studies. A machine learning approach was applied to explore how the mean accuracy of the cognitive workload classification accuracy varied across various sensing locations on the forehead such as the Left, Mid, Right, Left-Mid, Right-Mid and Whole forehead. The statistical significance analysis result showed that the Mid location could result in significant cognitive workload classification accuracy compared to Whole forehead sensing, with a statistically insignificant difference in the mean accuracy. Thus, the wearable fNIRS system can be improved in terms of wearability by optimizing the sensor location, considering the sensing of the Mid location on the forehead for cognitive workload monitoring.

The advent of powered prosthetic ankles provided more balance and optimal energy expenditure to lower amputee gait. However, these types of systems require an extensive setup where the parameters of the ankle, such as the amount of positive power and the stiffness of the ankle, need to be setup. Currently, calibrations are performed by experts, who base the inputs on subjective observations and experience. In this study, a novel evidence-based tuning method was presented using multi-channel electromyogram data from the residual limb, and a model for muscle activity was built. Tuning using this model requires an exhaustive search over all the possible combinations of parameters, leading to computationally inefficient system. Various data-driven optimization methods were investigated and a modified Nelder–Mead algorithm using a Latin Hypercube Sampling method was introduced to tune the powered prosthetic. The results of the modified Nelder–Mead optimization were compared to the Exhaustive search, Genetic Algorithm, and conventional Nelder–Mead method, and the results showed the feasibility of using the presented method, to objectively calibrate the parameters in a time-efficient way using biological evidence.