A Smart System to Overcome Sleep Inertia by Internet of Things (IoT) Through Environmental Regulation and Brain Wave Analysis

The utilization of internet-of-things (IoT) technology in healthcare has gained significant attention in recent years due to its potential to improve the management of chronic conditions and improve the quality of human life. In this study, a system is proposed to monitor light, temperature, and sound adjustments using an ESP32 microcontroller with Wi-Fi technology. Various control units (including light control units, temperature control units, and voice control units), ESP32 microcontrollers, and Blynk interface applications are used in this system to regulate environmental conditions in reducing sleep inertia experienced by the human body. Sleep inertia is a condition in which a person feels sleepy, confused, and experiences a decline in cognitive performance after waking up. This condition usually lasts for a few minutes to a few hours after waking up, especially if the individual wakes up from a deep sleep or has not slept enough. This phenomenon is often experienced by night shift workers, therefore there is a need for steps to overcome sleep inertia in workers who undergo night shifts. Based on the light, temperature, and sound settings using the Blynk application and the ESP32 microcontroller, the results showed that there was an increase in delta and theta wave values. To evaluate the system's effectiveness, participants were given clear information about the study's goals, data collection steps, and how to use the MUSE S EEG headband. Electroencephalography (EEG) data was recorded twice for each participant: before and after listening to jazz music. The Mind Monitor app, connected to the MUSE S headband via Bluetooth, was used to capture EEG signals. The data, focused on delta and theta brain waves, was analyzed using the Support Vector Machine (SVM) method. Data collection was carried out in a soundproof lab to ensure optimal conditions. The results of this increase are evidenced by the results of analysis using EEG Headband, where there is an increase of 0,03 for delta waves; and there was an increase of 0,1 for the Theta wave. This increase is also evidenced by analysis using SVM, where the magnitude of the accuracy value formed by precision, recall and F1 score has also increased. The magnitude of the value is for low-grade delta waves under initial conditions (0 lux, 32°C, 0 dB), which gives a value of precision of 1; recall of 0,94; F1 score of 0,97; and accuracy of 0,95. After applying the second condition (2000 lux, 17°C, 60 dB), the value increases to 1 precision; 0,99 drawdown; F1 score 1,00 and 1,00 accuracy. This proves that the increasing value of delta and theta waves will accelerate the loss of sleep inertia in the human body.