Recognising lifestyle activities of diabetic patients with a smartphone

Abstract

Abstract-Diabetes is both heavily affected by the patients' lifestyle, and it affects their lifestyle. Most diabetic patients can manage the disease without technological assistance, so we should not burden them with technology unnecessarily, but lifestylemonitoring technology can still be beneficial both for patients and their physicians. Because of that we developed an approach to lifestyle monitoring that uses the smartphone, which most patients already have. The approach consists of three steps. First, a number of features are extracted from the data acquired by smartphone sensors, such as the user's location from GPS coordinates and visible wi-fi access points, and the physical activity from accelerometer data. Second, several classifiers trained by machine learning are used to recognise the user's activity, such as work, exercise or eating. And third, these activities are refined by symbolic reasoning encoded in Event Calculus. The approach was trained and tested on five people who recorded their activities for two weeks each. Its classification accuracy was 0.88.

Passive Sensing of Health Outcomes Through Smartphones: Systematic Review of Current Solutions and Possible Limitations

“…In addition, 1 study tried to infer riding up and down an elevator [15], 1 assessed different activities including being stationary, limping, shuffling, and skipping [13], and 1 detected shopping and dining activities [14]. Physical activities were also explored in the sense of detecting and counting steps [26,27], distinguishing physical activity from lifestyle activities such as eating [28,29], assessing mobility in the elderly to avoid sedentary lives [30], studying its relationship with happiness including nonexercise activities [31-33], or even measuring and predicting the walking speed and distance of patients with pulmonary diseases [34].…”

Towards Breathing as a Sensing Modality in Depth-Based Activity Recognition

“…In [ 5 ], physiological data, including respiratory rate, obtained from a wearable sensing device is used as auxiliary modality to discriminate between four activity classes, namely lie, sit, walk and jog. To recognize lifestyle activities of diabetic patients [ 8 ], WiFi, GPS, sound and acceleration data from a smartphone, as well as heart rate and respiratory rate from a ECG monitor are used to distinguish ten different classes. The effects of respiratory rate on classification accuracy for the latter two studies however was not evaluated.…”

Passive Sensing of Health Outcomes Through Smartphones: Systematic Review of Current Solutions and Possible Limitations (Preprint)

“…In addition, 1 study tried to infer riding up and down an elevator [15], 1 assessed different activities including being stationary, limping, shuffling, and skipping [13], and 1 detected shopping and dining activities [14]. Physical activities were also explored in the sense of detecting and counting steps [26,27], distinguishing physical activity from lifestyle activities such as eating [28,29], assessing mobility in the elderly to avoid sedentary lives [30], studying its relationship with happiness including nonexercise activities [31][32][33], or even measuring and predicting the walking speed and distance of patients with pulmonary diseases [34].…”

“…Accelerometer [6][7][8][9][10][11][12][13][15][16][17][18][19][21][22][23][24][25][26][27][28]30,31,33,34,38,[111][112][113][114]; gyroscope [6,12,15,16,18,21,22,25,27,30,33,111,113,114]; magnetometer [6,16,18,21,27,111,113]; GPS [13,14,…”