Calvin Kuo

Falls in older adults lead to serious physical and mental consequences. An assessment of an older adult’s history of imbalance, characterized by their fall and near-fall history, is an imperative aspect of fall risk assessment. However, cognitive errors during the recall of imbalance events result in an inaccurate capture of fall risk. The detection of falls and near-falls using a wearable sensor system could allow for a quantifiable capture of imbalance for improved risk assessment. However, wearable systems often rely on the placement of sensors on specific locations of the body, limiting their adaptability for users and researchers. This thesis explores the development of an adaptable fall and near-fall detection system that can be deployed in multiple sensor placements. Furthermore, this thesis improves the near-fall detection ability of a multiclass system. Data was collected from 17 participants (9 females, 8 males) simulating 8 types of falls, 7 types of near-falls, and 8 types of activities of daily living. Participants were equipped with three inertial measurement units, placed on a combination of the lower back, thighs, sternum, and arms. The F1-score (harmonic mean of precision and recall) was assessed overall and for each movement category. A support vector machine trained with data aggregated across multiple sensor placements consistently detected imbalance events when tested on various sensor placements (Macro F1-score: 84.64 ± 5.57%). Models trained with data from a specific sensor placement led to decreases in the Macro F1-score of 29.87 ± 7.26% when tested on a different sensor placement. Although the placement-adaptable model demonstrated better overall performance, the detection of near-falls remained relatively poor (Near-Fall F1-score: 50.06 ± 31.42%). An incorporation of data before and after a suspected imbalance event increased the near-fall sensitivity by 31.35 ± 9.62% across multiple sensor placements. Furthermore, the addition of an RUSBoost model reduced class imbalances by screening 82.02% of non-imbalance events prior to classification. In conclusion, the development of an adaptable fall and near-fall detection system requires the collection of data across multiple sensor placements. Incorporation of contextual information can further augment performance, leading to a clinically relevant and user-friendly detection system.

View record

Inertial measurement units (IMUs) are a prevalent component in wearable sensor systems to study motion in unconstrained environments by measuring both linear acceleration and angular velocity at a point of interest on the human body. However, wearable sensors are often worn on soft tissue that is excited during impulsive impacts, producing dynamic soft tissue artifact measurement errors. This thesis quantifies the error caused by dynamic soft tissue artifacts to IMU sensors with different sensor mass and placement when mild impulsive impacts are delivered to the lower extremity using empirical signal analysis and model-based predictions.Data were collected from three IMU sensors attached at the anterior and posterior center of the dominant shank, and at the back of the ankle of 10 participants (5 females, 5 males). We varied the mass of the two shank IMUs from 5 grams to 37 grams in 8-gram increments. Impacts were generated by dropping the shank freely onto a foam pad placed on a force plate from a height of 21.6 cm.Ground truth vertical linear acceleration measurements from the ankle IMU were first cross-validated against the force plate. We then determined both posterior and anterior IMUs overestimated the ground truth peak vertical linear acceleration measurement by 117.9% and 55.1%, respectively. The posterior IMU had greater overestimations, suggesting more severe dynamic soft tissue artifacts, while errors generally decreased with increasing mass, suggesting a mitigating effect from adding sensor mass. We next assessed post-impact oscillations, which we determined lasted 0.32±0.07 seconds with a frequency of 9.79±2.68 Hz on the posterior and 0.15±0.05 seconds with a frequency of 18.33±12.24 Hz on the anterior. As sensor weight increased, the oscillation duration increased linearly while the frequency decreased for both anterior and posterior IMUs. This suggests that increasing sensor mass amplifies post-impact dynamic soft tissue artifact errors. These results and dependencies were confirmed by modeling dynamic soft tissue artifacts as double spring mass damper systems.In conclusion, the dynamic soft tissue artifacts directly relate to the accuracy of kinematic measurement in IMU sensors with a dependence on sensor mass and placement.

View record