Wearable sensor-based fall detection for elderly care using ensemble machine learning techniques

Older people face serious issues with unintentional collisions that result in healthcare admissions and fatalities. Since numerous accidents happen quickly, it might be difficult to identify crashes in context. Enhancing the quality of services for older people requires the development of a computerized surveillance network that can anticipate accidents before occur, offer protection throughout the incident, and send out remote warnings following an accident. This research suggested a wearing surveillance system that seeks to detect accidents at the onset and lineage, triggering an alarm to reduce damages caused by accidents and sending out an external alert when the human body hits the hard surface. Meanwhile, the research's offsite evaluation of a combined structure utilizing the Random Forest technique (RF), Supporting Vectors Machines (SVM), and available information were used to illustrate this idea. The suggested method employed RF to reliably retrieve features from speedometer and inertial facts, while SVM provides an estimator and classification-capable method. Each module in the unique category-based composite structure is recognized at a certain level. The suggested strategy outperformed modern fall identification techniques when tested using the labeled KFall database, achieving average precision of 95 percent, 96 percent, as well as 98 percent for Non-Falls, Pre-Falls, as well as detectable fall incidents, correspondingly. The whole assessment proved the algorithmic learning structure's efficacy. Older people's standard of existence will increase, and accidents will be avoided because of such smart tracking devices.