In the last years, research on techniques able to classify activities of daily living and to detect falls is very active. Many application domains will benefit from these techniques, first of all …
Ambient Assisted Living
The research field concerning techniques able to recognize and monitor human activities is very active in recent years. Such techniques can be applied in several application domains spanning from leisure to health care.
In this domain, we are both investigating new techniques for human activity recognition based on accelerometric patterns from smartphones, and building a new dataset containing both activities of daily livings (ADLs) and falls.
Life expectancy keeps growing and, among elderly people, accidental falls occur frequently. A system able to promptly detect falls would help in reducing the injuries that a fall could cause. Such a …
UniMiB SHAR (UniMiB Smartphone-based Human Activity Recognition) is a new dataset of smartphone accelerometer data. The dataset was created with the aim of providing to the scientific community a rich and complete dataset of acceleration pattern captured by smartphones to be used as a common benchmark for the evaluation of human activity recognition techniques.