We live in a generation that is hard-pressed for time and that, arguably, has a lack of compassion. As a result of this negligence, the old and feeble are unfortunately forgotten. The institutions of assisted care environments mushroomed as a result of this frightening trend. Loss of consciousness and fall-induced injury is one of the foremost problems faced by the elderly. They are the primary cause for the transfer of senior citizens from the comfort of their residence to assisted care environments. They also account for 40% of injury-related deaths and the absence of timely action can prove incurable.
This system is to ensure the doctor which patient is in risk of falling. MPU-6050 will take the reading of acceleration and gyro readings in different positions and these readings will be transmitted to the cloud using google cloud interface. This real-time data is presented in the form of a table and graph. These readings can be accessed by any doctor who is having a particular URL. By applying the Machine Learning model on these readings, the doctor can ensure that which patient is in need of fall detection. The device mustn’t be cumbersome, but rather wearable, so as to remove any social stigma related to the possession of such a device. It must have a high degree of reliability and differentiate activities of daily life from genuine falls.
Components Used/Type of Coding
- Raspberry Pi
- Internet of Things (IoT)
- Machine Learning
A robust fall detection having a high degree of reliability and the ability to differentiate the activities of daily life from genuine falls is the need of an hour, which will alleviate the burden of caregivers and resource-strained conditions in the health care fields. Fall detection and prediction are very crucial research in this new era to reduce the number of fatal falls which leads to injuries related to death.