Recognition of Daily Gestures with Wearable Inertial Rings and Bracelets.

Recognition of activities of daily living plays an important role in monitoring elderly people and helping caregivers in controlling and detecting changes in daily behaviors. Thanks to the miniaturization and low cost of Microelectromechanical systems (MEMs), in particular of Inertial Measurement Units, in recent years body-worn activity recognition has gained popularity. In this context, the proposed work aims to recognize nine different gestures involved in daily activities using hand and wrist wearable sensors. Additionally, the analysis was carried out also considering different combinations of wearable sensors, in order to find the best combination in terms of unobtrusiveness and recognition accuracy. In order to achieve the proposed goals, an extensive experimentation was performed in a realistic environment. Twenty users were asked to perform the selected gestures and then the data were off-line analyzed to extract significant features. In order to corroborate the analysis, the classification problem was treated using two different and commonly used supervised machine learning techniques, namely Decision Tree and Support Vector Machine, analyzing both personal model and Leave-One-Subject-Out cross validation. The results obtained from this analysis show that the proposed system is able to recognize the proposed gestures with an accuracy of 89.01% in the Leave-One-Subject-Out cross validation and are therefore promising for further investigation in real life scenarios.

Upper limb motor pre-clinical assessment in Parkinson's disease using machine learning.

INTRODUCTION: Parkinson's disease (PD) is a common neurodegenerative disorder characterized by disabling motor and non-motor symptoms. For example, idiopathic hyposmia (IH), which is a reduced olfactory sensitivity, is typical in >95% of PD patients and is a preclinical marker for the pathology. METHODS: In this work, a wearable inertial device, named SensHand V1, was used to acquire motion data from the upper limbs during the performance of six tasks selected by MDS-UPDRS III. Three groups of people were enrolled, including 30 healthy subjects, 30 IH people, and 30 PD patients. Forty-eight parameters per side were computed by spatiotemporal and frequency data analysis. A feature array was selected as the most significant to discriminate among the different classes both in two-group and three-group classification. Multiple analyses were performed comparing three supervised learning algorithms, Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes, on three different datasets. RESULTS: Excellent results were obtained for healthy vs. patients classification (F-Measure 0.95 for RF and 0.97 for SVM), and good results were achieved by including subjects with hyposmia as a separate group (0.79 accuracy, 0.80 precision with RF) within a three-group classification. Overall, RF classifiers were the best approach for this application. CONCLUSION: The system is suitable to support an objective PD diagnosis. Further, combining motion analysis with a validated olfactory screening test, a two-step non-invasive, low-cost procedure can be defined to appropriately analyze people at risk for PD development, helping clinicians to identify also subtle changes in motor performance that characterize PD onset.

Comparative Motor Pre-clinical Assessment in Parkinson's Disease Using Supervised Machine Learning Approaches.

Millions of people worldwide are affected by Parkinson's disease (PD), which significantly worsens their quality of life. Currently, the diagnosis is based on assessment of motor symptoms, but interest toward non-motor symptoms is increasing, as well. Among them, idiopathic hyposmia (IH) is associated with an increased risk of developing PD in healthy adults. In this work, a wearable inertial device, named SensFoot V2, was used to acquire motor data from 30 healthy subjects, 30 people with IH, and 30 PD patients while performing tasks from the MDS-UPDRS III for lower limb assessment. The most significant and non-correlated extracted parameters were selected in a feature array that can identify differences between the three groups of people. A comparative classification analysis was performed by applying three supervised machine learning algorithms. The system resulted able to distinguish between healthy and patients (specificity and recall equal to 0.967), and the people with IH can be identified as a separate class within a three-group classification (accuracy equal to 0.78). Thus, the system could support the clinician in objective assessment of PD. Further, identification of IH together with changes in motor parameters could be a non-invasive two-step approach to investigate the early onset of PD.