The merge of new sensing technologies with machine learning methods can be used as a tool to recognize complex activities. A wearable particulate matter (PM) sensor, in combination with a motion tracker, was provided to 97 individuals for 7 days in two seasons. These data sets were used in three different models, constructed by the classification of activity. Using algorithms IBk, J48 and RandomForest for hourly (minute) values, an accuracy of 31.0 (23.1)%, 28.6 (22.0)% and 35.7 (23.0)%, respectively, was achieved. Most misclassified instances concern vaguely defined activities. Low accuracy can also be explained with the differences in time scales. The accuracy could be improved by more clearly defining the activities and collecting per-minute data
Low-cost environmental and motion sensor data for complex activity recognition: proof of concept
Sarigiannis D.;Horvat M.
2021-01-01
Abstract
The merge of new sensing technologies with machine learning methods can be used as a tool to recognize complex activities. A wearable particulate matter (PM) sensor, in combination with a motion tracker, was provided to 97 individuals for 7 days in two seasons. These data sets were used in three different models, constructed by the classification of activity. Using algorithms IBk, J48 and RandomForest for hourly (minute) values, an accuracy of 31.0 (23.1)%, 28.6 (22.0)% and 35.7 (23.0)%, respectively, was achieved. Most misclassified instances concern vaguely defined activities. Low accuracy can also be explained with the differences in time scales. The accuracy could be improved by more clearly defining the activities and collecting per-minute dataI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
