Falls among elderly individuals are a major public health concern, leading to significant health complications, disability, and even fatalities. According to the 2011 Census, disability is more prevalent in older adults, with one-third of individuals aged 65 and above experiencing a fall annually. Falls are defined as “unexpected events in which the participant comes to rest on the ground, floor, or lower level” and are a primary cause of injury-related deaths among older adults. The age-adjusted fall death rate has risen by 30%, reaching 64 deaths per 100,000 older adults. Beyond physical injuries, the psychological impact of falling increases the fear of future falls, leading to reduced physical activity, muscle weakness, and a heightened risk of subsequent falls. Studies show that experiencing a fall doubles the chances of falling again, emphasizing the need for an effective fall detection and response system.
Injuries resulting from falls can often be mitigated if immediate assistance is provided. However, due to the increasing number of elderly individuals living alone or with limited supervision, falls frequently go unnoticed, delaying critical medical intervention. According to Statistics Indonesia (2014), the elderly population (aged 60 and above) comprised 8.03% of the total population, highlighting the growing need for fall monitoring solutions. Given the rising population of older adults, there is an urgent requirement for automated fall detection systems that can alert caregivers in real-time.
This study proposes a wearable fall detection system leveraging an ESP8266 microcontroller and an MPU6050 sensor (accelerometer + gyroscope). The waist-mounted device continuously monitors the user’s motion and classifies activities based on pre-defined thresholds. This solution provides timely intervention, reducing injury risks and enabling caregivers to respond immediately, ultimately improving elderly safety and well-being.