Main Content

Every year, one-third to one-half of the population aged 65 and over experience falls. Falls are the leading cause of injury in older adults and the leading cause of accidental death in those 75 years of age and older. For a human, experiencing a fall unobserved can be doubly dangerous. The obvious possibility of initial injury may be further aggravated by the possible consequences if treatment is not obtained within a short time. Statistics show that the majority of serious consequences are not the direct result of falling, but rather are due to a delay in assistance and treatment. Post-fall consequences can be greatly reduced if relief personnel can be alerted in time. Many elderly live alone either in an apartment or a smaller house after their children have grown up and left home. It is not uncommon after a fall that an elderly person is unable to get up by themselves or summon help. There is therefore a need for an automatic fall detection system in which a patient can summon help even if they are unconscious or unable to get up after the fall. Many algorithms have been developed bu till now it is difficult to distinguish real falls from certain fall-like activities such as sitting down quickly and jumping, resulting in many false positives. Most of the algorithms use accelerometer to detect fall with body orientation, but it is not very useful when the ending position is not horizontal, e.g. falls happen on stairs. I made a novel fall detection system using both accelerometers and gyroscopes and for that my algorithm reduces both false positives and false negatives, while improving fall detection accuracy. My system instantly notifies to a concern person with SMS and Email when fall occurred. It has also a panic button and an emergency notification can be sent by pressing it.”

Link to article