SPARE: A Spectral Peak Recovery Algorithm for PPG Signals Pulsewave Reconstruction in Multimodal Wearable Devices.

The photoplethysmographic (PPG) signal is an unobtrusive blood pulsewave measure that has recently gained popularity in the context of the Internet of Things. Even though it is commonly used for heart rate detection, it has been lately employed on multimodal health and wellness monitoring applications. Unfortunately, this signal is prone to motion artifacts, making it almost useless in all situations where a person is not entirely at rest. To overcome this issue, we propose SPARE, a spectral peak recovery algorithm for PPG signals pulsewave reconstruction. Our solution exploits the local semiperiodicity of the pulsewave signal, together with the information about the cardiac rhythm provided by an available simultaneous ECG, to reconstruct its full waveform, even when affected by strong artifacts. The developed algorithm builds on state-of-the-art signal decomposition methods, and integrates novel techniques for signal reconstruction. Experimental results are reported both in the case of PPG signals acquired during physical activity and at rest, but corrupted in a systematic way by synthetic noise. The full PPG waveform reconstruction enables the identification of several health-related features from the signal, showing an improvement of up to 65% in the detection of different biomarkers from PPG signals affected by noise.

Multi-Modal Acute Stress Recognition Using Off-the-Shelf Wearable Devices.

Monitoring stress and, in general, emotions has attracted a lot of attention over the past few decades. Stress monitoring has many applications, including high-risk missions and surgical procedures as well as mental/emotional health monitoring. In this paper, we evaluate the possibility of stress and emotion monitoring using off-the-shelf wearable sensors. To this aim, we propose a multi-modal machine-learning technique for acute stress episodes detection, by fusing the information careered in several biosignals and wearable sensors. Furthermore, we investigate the contribution of each wearable sensor in stress detection and demonstrate the possibility of acute stress recognition using wearable devices. In particular, we acquire the physiological signals using the Shimmer3 ECG Unit and the Empatica E4 wristband. Our experimental evaluation shows that it is possible to detect acute stress episodes with an accuracy of 84.13%, for an unseen test set, using multi-modal machinelearning and sensor-fusion techniques.

Real-Time Cognitive Workload Monitoring Based on Machine Learning Using Physiological Signals in Rescue Missions.

High levels of cognitive workload decreases human's performance and leads to failures with catastrophic outcomes in risky missions. Today, reliable cognitive workload detection presents a common major challenge, since the workload is not directly observable. However, cognitive workload affects several physiological signals that can be measured non-invasively. The main goal of this work is to develop a reliable machine learning algorithm to identify the cognitive workload induced during rescue missions, which is evaluated through drone control simulation experiments. In addition, we aim to minimize the computing resources usage while maximizing the cognitive workload detection accuracy for a reliable real-time operation. We perform an experiment in which 24 subjects played a rescue mission simulator while respiration, electrocardiogram, photoplethysmogram, and skin temperature signals were measured. State-of-the-art feature-based machine learning algorithms are investigated for cognitive workload characterization using learning curves, data augmentation, and cross-validation techniques. The best classification algorithm is selected, optimized, and the most informative features are selected. Finally, the generalization power of the optimized model is evaluated on an unseen test set. We obtain an accuracy level of 86% on the new unseen datasets using the proposed and optimized eXtreme Gradient Boosting (XGB) algorithm. Then, we reduce the complexity of the machine learning model for future implementation on resource-constrained wearable embedded systems, by optimizing the model and selecting the 26 most important features. Overall, a generalizable and low-complexity machine learning model for cognitive workload detection based on physiological signals is presented for the first time in the literature.