AI-Enabled Smart Wristband Providing Real-Time Vital Signs and Stress Monitoring

Abstract

This work introduces the design, architecture, implementation, and testing of a low-cost and machine-learning-enabled device to be worn on the wrist. The suggested wearable device has been developed for use during emergency incidents of large passenger ship evacuations, and enables the real-time monitoring of the passengers' physiological state, and stress detection. Based on a properly preprocessed PPG signal, the device provides essential biometric data (pulse rate and oxygen saturation level) and an efficient unimodal machine learning pipeline. The stress detecting machine learning pipeline is based on ultra-short-term pulse rate variability, and has been successfully integrated into the microcontroller of the developed embedded device. As a result, the presented smart wristband is able to provide real-time stress detection. The stress detection system has been trained with the use of the publicly available WESAD dataset, and its performance has been tested through a two-stage process. Initially, evaluation of the lightweight machine learning pipeline on a previously unseen subset of the WESAD dataset was performed, reaching an accuracy score equal to 91%. Subsequently, external validation was conducted, through a dedicated laboratory study of 15 volunteers subjected to well-acknowledged cognitive stressors while wearing the smart wristband, which yielded an accuracy score equal to 76%.

Keywords: biometric sensor; blood pulse; machine learning; smart wristband; stress detection; wearable.

Figure 2

PPG technique and output signal: on the left, a LED of the PPG sensor emits light into the wrist’s skin, and the photodetector absorbs the reflection; on the right, the output signal of the used MAX30101 sensor, inverted to reflect the correct morphological representation, with visible systolic and diastolic points [48].

Figure 1

System architecture.

Figure 3

PCB after the SMT assembly, with all the necessary components: (a) top side; (b) bottom side.

Figure 4

3D design of the enclosure (casing and sliding lid): (a) mechanical 3D design; (b) mechanical drawing with dimensions.

Figure 5

Smart wristband on the wrist.

Figure 6

Process flow of the smart wristband.

Figure 7

Pulse rate calculation pipeline.

Figure 8

Stages of PPG processing.

Figure 9

Pulse Rate - Smart wristband vs Empatica E4.

Figure 10

$Sp{O}_2$ calculation pipeline.

Figure 11

Oxygen saturation percentage: smart wristband vs commercial finger-based oximeter.

Figure 12

Stress detection model pipeline.

Figure 13

Confusion matrix.