Measuring and Classifying Land-Based and Water-Based Daily Living Activities Using Inertial Sensors

Abstract

Abstract:This study classified motions of typical daily activities in both environments using inertial sensors attached at the chest and thigh to determine the optimal site to attach the sensors. Walking, chair standing and sitting, and step climbing were conducted both in water and on land. A mean, variance and skewness for acceleration data was calculated. A Neural Network and Decision Tree algorithm was applied for classifying each motion in both environments. In total, 126 and 144 samples of thigh and chest data sets were obtained for analysis in each condition. For the chest data, the algorithm correctly classified 80% of the water-based activities, and 90% of the land-based. Whilst the thigh sensor correctly classified 97% of water-based and 100% of land-based activities. The inertial sensor placed on the thigh provided the most appropriate protocol for classifying motions for land-based and water-based typical daily life activities.

The features of muscle activity during chair standing and sitting motion in submerged condition

“…Other directions of research are the implementation of pace setting and assessment of the effects of chair surface height and water depth. Previous studies on walking and running classified pace as slow, normal, or fast [13, 21, 27]; however, the present study included exercises that were performed only at a pace that was comfortable for the individual participants. Further investigations involving several pace settings are needed in order to elucidate the detailed features of chair-based/standing exercises in submerged conditions.…”

“…The height of the steel box was 40 cm, as described in a previous study [4]. The exercise intensity was set at a self-selected comfortable pace [13, 14, 21]. In the submerged condition, the depth of the swimming pool was set at 1 m, where the depth from the water's surface to the chair's sitting surface was 60 cm, equivalent to the clavicle level of each participant.…”

“…The EMG and motion capture data were collected from the beginning to the end of each sit-to-stand and stand-to-sit movement based on the angular velocity of the trunk segment. The threshold value was set at < or > 0.087 rad∙s-1 (5° per second) according to a previous study [7, 21]. The collected data were divided into three phases: phase 1 (P1) comprised the beginning of the sit-to-stand movement to the beginning of knee joint extension (the threshold of the knee joint angular velocity was set at 0.087 rad∙s -1 [5° per second]), phase 2 (P2) comprised the beginning of knee joint extension to the reversal of trunk segment flexion–extension, and phase 3 (P3) comprised the reversal of trunk segment flexion–extension to the end of sit-to-stand in the sit-to-stand movement.…”