Peer Review #2 of "Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study (v0.1)"

Abstract

Background: Wearable activity trackers are regarded as a new opportunity to deliver health promotion interventions. The algorithms typically contain two stages: 1) activity classification and 2) quantification of energy expenditures by applying activity-specific regression equations. Although the predictions of traditional activity trackers rely primarily on the processing of accelerometer sensor data, the emergence of smart clothes with multi-sensing capacities could contribute to a more accurate evaluation of daily physical behaviors. This study aims to 1) develop an activity recognition algorithm based on the processing of plantar pressure information provided by a smart-shoe prototype and 2) to determine the optimal hardware and software configurations. Method: Seventeen subjects wore a pair of smart-shoe prototypes composed of plantar pressure measurement insoles, and they performed the following nine activities: sitting, standing, walking on a flat surface, walking upstairs, walking downstairs, walking up a slope, running, cycling, and completing office work. The insole featured seven pressure sensors. For each activity, four minutes of plantar pressure data were collected. The plantar pressure data were cut in overlapping windows of different lengths and 167 features were extracted for each window. A random forest model was trained to recognize activity using some selected sensor configurations and different numbers of data features. The resulting activity recognition algorithms were evaluated using data samples specifically directed to validation trials. Results: Using all the sensors and all 167 features, the smart shoes predicted the activities with an average success of 89%. "Running" demonstrated the highest percentage of good predictions (100%). "Walking up a slope" was linked with the lowest performance (63%), with the majority of the false positives being "walking on a flat surface" and "walking upstairs." Some 2-and 3-sensor configurations were linked with an