Drowsiness

Solution: Drowsiness

Drowsiness is a state of increased situational sleepiness associated with reduced alertness, slower reactions, and a greater tendency to fall asleep (Hu and Lodewijks, 2020). It impairs focus and responsiveness, especially during prolonged or repetitive tasks. Drowsiness is driven by a combination of sleep debt (how long it has been since a person last slept) and the body’s internal 24-hour clock. Sleep is the most effective way to relieve drowsiness.

Eye Tracking: Eye tracking is a sensitive, quantifiable, accurate real-time measure of sleepiness and drowsiness. Changes in blink behavior, such as blink rate, blink duration, and blink variability, are especially indicative of increasing drowsiness (Barbato et al. 1995; Caffier et al., 2003; Schleicher et al., 2008; Cori et al., 2019; Abe, 2023). These eye-based signals reflect the physiological progression from alertness toward sleep and offer a non-invasive way to monitor drowsiness as it develops.

HarmonEyes uses the eye tracking signal, machine learning and AI to answer the following questions related to drowsiness:

1. What is your current level of drowsiness?
   • Alert: High alertness and responsiveness. No meaningful sleep pressure. Cognitive and physical performance are unimpaired, with substantial reserve available for sustained or demanding tasks.
   • Neither Alert nor Drowsy: Neutral state. Neither heightened alertness nor pronounced sleepiness. Performance is generally stable, though vigilance may be more sensitive to task demands or time-on-task.
   • Rather Drowsy: Early signs of sleepiness. Subtle reductions in alertness and responsiveness may be present. Increased effort is required to maintain focus, particularly during monotonous or sustained tasks.
   • Drowsy: Elevated sleepiness consistent with drowsiness. Difficulty maintaining alertness, slowed reactions, and increased risk of attentional lapses. At higher levels, individuals may be fighting sleep or experiencing brief sleep intrusions, leading to significant performance impairment and increased safety risk.
2. When will drowsiness level change?
   1. Predicted future load level:
      1. Alert
      2. Neither alert nor drowsy
      3. Rather Drowsy
      4. Drowsy
   2. Time to reach future state:
      1. Minutes
   3. Confidence Interval (0-1, low-high)
      1. For each output of drowsiness