Real-Time EEG-Based Cognitive Workload Monitoring on Wearable Devices.

OBJECTIVE: Cognitive workload monitoring (CWM) can enhance human-machine interaction by supporting task execution assistance considering the operator's cognitive state. Therefore, we propose a machine learning design methodology and a data processing strategy to enable CWM on resource-constrained wearable devices. METHODS: Our CWM solution is built upon edge computing on a simple wearable system, with only four peripheral channels of electroencephalography (EEG). We assess our solution on experimental data from 24 volunteers. Moreover, to overcome the system's memory constraints, we adopt an optimization strategy for model size reduction and a multi-batch data processing scheme for optimizing RAM memory footprint. Finally, we implement our data processing strategy on a state-of-the-art wearable platform and assess its execution and system battery life. RESULTS: We achieve an accuracy of 74.5% and a 74.0% geometric mean between sensitivity and specificity for CWM classification on unseen data. Besides, the proposed model optimization strategy generates a 27.5x smaller model compared to the one generated with default parameters, and the multi-batch data processing scheme reduces RAM memory footprint by 14x compared to a single batch data processing. Finally, our algorithm uses only 1.28% of the available processing time, thus, allowing our system to achieve 28.5 hours of battery life. CONCLUSION: We provide a reliable and optimized CWM solution using wearable devices, enabling more than a day of operation on a single battery charge. SIGNIFICANCE: The proposed methodology enables real-time data processing on resource-constrained devices and supports real-time wearable monitoring based on EEG for applications as CWM in human-machine interaction.

Robust Epileptic Seizure Detection on Wearable Systems with Reduced False-Alarm Rate.

Epilepsy affects more than 50 million people and ranks among the most common neurological diseases worldwide. Despite advances in treatment, one-third of patients still suffer from refractory epilepsy. Wearable devices for real-time patient monitoring can potentially improve the quality of life for such patients and reduce the mortality rate due to seizure-related accidents and sudden death in epilepsy. However, the majority of employed seizure detection techniques and devices suffer from unacceptable false-alarm rate. In this paper, we propose a robust seizure detection methodology for a wearable platform and validate it on the Physionet.org CHB-MIT Scalp EEG database. It reaches sensitivity of 0.966 and specificity of 0.925, and reducing the false-alarm rate by 34.7%. We also evaluate the battery lifetime of the wearable system including our proposed methodology and demonstrate the feasibility of using it in real time for up to 40.87 hours on a single battery charge.

Information Formulation of the UDU Kalman Filter.

A new information formulation of the Kalman filter is presented where the information matrix is parameterized as the product of an upper triangular matrix, a diagonal matrix, and the transpose of the triangular matrix (UDU factorization). The UDU factorization of the Kalman filter is known for its numerical stability, this work extends the technique to the information filter. A distinct characteristic of the new algorithm is that measurements can be processed as vectors, while the classic UDU factorization requires scalar measurement processing, i.e. a diagonal measurement noise covariance matrix.

Current perception threshold and reaction time in the assessment of sensory peripheral nerve fibers through sinusoidal electrical stimulation at different frequencies

INTRODUCTION: The Perception Sensory Threshold (ST) for sinusoidal current stimuli at 5, 250, and 2,000 Hz is commonly used in the assessment of peripheral nerve fibers (C, Aδ, and Aβ, respectively). However, the neuroselectivity of these frequencies is far from consensus. In addition, Reaction Time (RT) measurements suggest that 2,000 Hz stimuli excite Aβ-fibers, 250 Hz Aβ- or Aδ-fibers, as well as 5 Hz Aβ-, Aδ- or C-fibers. Therefore, we suppose that the sinusoidal current neuroselectivity may be better observed if ST and RT parameters are jointly evaluated. In addition, we have investigated whether there are other sets of frequencies that could be used. METHODS: Thus this work investigates ST and RT for stimuli with frequency ranging from 1 to 3,000 Hz, on 28 healthy subjects aged from 19 to 44 years old (27.1±5.49). ST and RT dissimilarity among different frequencies was evaluated applying bi-dimensional Fisher Quadratic Discriminant. RESULTS: The lowest classification error (3.6%) was obtained for 1, 250, and 3,000 Hz. Error for 5, 250, and 2,000Hz was 16.7%. Stimulation frequency at 1 Hz evoked more sensations related to C-fibers (53% of reports) than to Aβ-fibers (36%). However, this behavior did not repeat itself at 5 Hz (only 21% of perceptions were related to C-fibers against 64% to Aβ-fibers). Sensations related to Aβ-fibers prevailed for the highest frequencies presented to the subjects (2,000 Hz - 82% and 3,000 Hz - 93%). Mean RT values showed a decreasing trend with frequency. CONCLUSION: These results suggest that frequencies 1, 250, and 3,000 Hz are more neuroselective than 5, 250, and 2,000 Hz for the evaluation of peripheral sensitive fibers. Furthermore, they show RT usefulness.