Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders

Smartwatches provide technology-based assessments in Parkinson’s Disease (PD). It is necessary to evaluate their reliability and accuracy in order to include those devices in an assessment. We present unique results for sensor validation and disease classification via machine learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches throughout a 15-min examination. Symptoms and medical history were captured on the paired smartphone. The amplitude error of both smartwatches reaches up to 0.005 g, and for the measured frequencies, up to 0.01 Hz. A broad range of different ML classifiers were cross-validated. The most advanced task of distinguishing PD vs. DD was evaluated with 74.1% balanced accuracy, 86.5% precision and 90.5% recall by Multilayer Perceptrons. Deep-learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle tremor signs with low noise. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers, but it remains challenging for distinguishing similar disorders.

Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders

Smartwatches provide technology-based assessments in Parkinson’s disease (PD). We present results for sensor validation and disease classification via Machine Learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches and within a 15-min examination. Symptoms and medical history were captured on the paired smartphone. A broad range of different ML classifiers were cross-validated. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. The most advanced task of distinguishing PD vs DD was evaluated with 74,1% balanced accuracy, 86,5% precision and 90,5% recall by Multilayer Perceptrons. Deep Learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle-tremor signs with low noise. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers but it remains challenging for distinguishing similar disorders.

Integrated Fault Evaluation Through Fusion Algorithm Supported by Kalman Filter

An Integrated Fault Evaluation (IFE) process is proposed in this study. It includes Sensor Validation (SV), Fault Detection (FD) and Fault Source Identification (FSI). The proposed algorithm employs data fusion algorithm enhanced by Kalman filter (KF). As the case study, vibration signals representing different aging states of an induction motor are used. The vibration data collected from two identical sensors with different measurement and process noises are achieved. Through the statistical and frequency domain characteristics, IFE is realized. The most prominent contribution of the study is the capability of distinction between the aging of the system and the process problems. For this aim, a rate representing the healthiness, which can discern the impact of the process noise and system aging, is calculated.

Data assimilation in hydrodynamic models for system-wide soft sensing and sensor validation for urban drainage tunnels

Tunnels are increasingly used worldwide to expand the capacity of urban drainage systems, but they are difficult to monitor with sensors alone. This study enables soft sensing of urban drainage tunnels by assimilating water level observations into an ensemble of hydrodynamic models. Ensemble-based data assimilation is suitable for non-linear models and provides useful uncertainty estimates. To limit the computational cost, our proposed scheme restricts the assimilation and ensemble implementation to the tunnel and represents the surrounding drainage system deterministically. We applied the scheme to a combined sewer overflow tunnel in Copenhagen, Denmark, with two sensors 3.4 km apart. The downstream observations were assimilated, while those upstream were used for validation. The scheme was tuned using a high-intensity event and validated with a low-intensity one. In a third event, the scheme was able to provide soft sensing as well as identify errors in the upstream sensor with high confidence.

Sensor Validation for Indoor Air Quality using Machine Learning

To guarantee a high indoor air quality is an increasingly important task. Sensors measure pollutants in the air and allow for monitoring and controlling air quality. However, all sensors are susceptible to failures, either permanent or transitory, that can yield incorrect readings. Automatically detecting such faulty readings is therefore crucial to guarantee sensors' reliability. In this paper we evaluate three Machine Learning algorithms applied to the task of classifying a single reading from a sensor as faulty or not, comparing them to standard statistical approaches. We show that all tested machine learning methods -- Multi-layer Perceptron, K-Nearest Neighbor and Random Forest -- outperform their statistical counterparts, both by allowing better separation boundaries and by allowing for the use of contextual information. We further show that this result does not depend on the amount of data, but ML methods are able to continue to improve as more data is made available.

Sensing Systems for Respiration Monitoring: A Technical Systematic Review

Respiratory monitoring is essential in sleep studies, sport training, patient monitoring, or health at work, among other applications. This paper presents a comprehensive systematic review of respiration sensing systems. After several systematic searches in scientific repositories, the 198 most relevant papers in this field were analyzed in detail. Different items were examined: sensing technique and sensor, respiration parameter, sensor location and size, general system setup, communication protocol, processing station, energy autonomy and power consumption, sensor validation, processing algorithm, performance evaluation, and analysis software. As a result, several trends and the remaining research challenges of respiration sensors were identified. Long-term evaluations and usability tests should be performed. Researchers designed custom experiments to validate the sensing systems, making it difficult to compare results. Therefore, another challenge is to have a common validation framework to fairly compare sensor performance. The implementation of energy-saving strategies, the incorporation of energy harvesting techniques, the calculation of volume parameters of breathing, or the effective integration of respiration sensors into clothing are other remaining research efforts. Addressing these and other challenges outlined in the paper is a required step to obtain a feasible, robust, affordable, and unobtrusive respiration sensing system.