RESUMO
Monitoring systems assist farmers in monitoring the health of dairy cows by predicting behavioral patterns (e.g., lying) and their changes with machine learning models. However, the available systems were developed either for indoors or for pasture and fail to predict the behavior in other locations. Therefore, the goal of our study was to train and evaluate a model for the prediction of lying on a pasture and in the barn. On three farms, 7-11 dairy cows each were equipped with the prototype of the monitoring system containing an accelerometer, a magnetometer and a gyroscope. Video observations on the pasture and in the barn provided ground truth data. We used 34.5 h of datasets from pasture for training and 480.5 h from both locations for evaluating. In comparison, random forest, an orientation-independent feature set with 5 s windows without overlap, achieved the highest accuracy. Sensitivity, specificity and accuracy were 95.6%, 80.5% and 87.4%, respectively. Accuracy on the pasture (93.2%) exceeded accuracy in the barn (81.4%). Ruminating while standing was the most confused with lying. Out of individual lying bouts, 95.6 and 93.4% were identified on the pasture and in the barn, respectively. Adding a model for standing up events and lying down events could improve the prediction of lying in the barn.
RESUMO
Objective and rater independent analysis of movement impairment is one of the most challenging tasks in medical engineering. Especially assessment of motor symptoms defines the clinical diagnosis in Parkinson's disease (PD). A sensor-based system to measure the movement of the upper and lower extremities would therefore complement the clinical evaluation of PD. In this study two different sensor-based systems were combined to assess movement of 18 PD patients and 17 healthy controls. First, hand motor function was evaluated using a sensor pen with integrated accelerometers and pressure sensors, and second, gait function was assessed using a sports shoe with attached inertial sensors (gyroscopes,accelerometers).Subjects performed standardized tests for both extremities.Features were calculated from sensor signals to differentiate between patients and controls. For the latter, pattern recognition methods were used and the performance of four classifiers was compared. In a first step classification was done for every single system and in a second step for combined features of both systems. Combination of both motor task assessments substantially improved classification rates to 97%using the AdaBoost classifier for the experiment patients vs.controls.The combination of two different analysis systems led to enhanced, more stable, objective, and rater independent recognition of motor impairment. The method can be used as a complementary diagnostic tool for movement disorders.
