Physical activity recognition based on rotated acceleration data using quaternion in sedentary behavior: a preliminary study

The Pragmatic Classification of Upper Extremity Motion in Neurological Patients: A Primer

Recent advances in wearable sensor technology and machine learning (ML) have allowed for the seamless and objective study of human motion in clinical applications, including Parkinson's disease, and stroke. Using ML to identify salient patterns in sensor data has the potential for widespread application in neurological disorders, so understanding how to develop this approach for one's area of inquiry is vital. We previously proposed an approach that combined wearable inertial measurement units (IMUs) and ML to classify motions made by stroke patients. However, our approach had computational and practical limitations. We address these limitations here in the form of a primer, presenting how to optimize a sensor-ML approach for clinical implementation. First, we demonstrate how to identify the ML algorithm that maximizes classification performance and pragmatic implementation. Second, we demonstrate how to identify the motion capture approach that maximizes classification performance but reduces cost. We used previously collected motion data from chronic stroke patients wearing off-the-shelf IMUs during a rehabilitation-like activity. To identify the optimal ML algorithm, we compared the classification performance, computational complexity, and tuning requirements of four off-the-shelf algorithms. To identify the optimal motion capture approach, we compared the classification performance of various sensor configurations (number and location on the body) and sensor type (IMUs vs. accelerometers). Of the algorithms tested, linear discriminant analysis had the highest classification performance, low computational complexity, and modest tuning requirements. Of the sensor configurations tested, seven sensors on the paretic arm and trunk led to the highest classification performance, and IMUs outperformed accelerometers. Overall, we present a refined sensor-ML approach that maximizes both classification performance and pragmatic implementation. In addition, with this primer, we showcase important considerations for appraising off-the-shelf algorithms and sensors for quantitative motion assessment.

Recognition of Sedentary Behavior by Machine Learning Analysis of Wearable Sensors during Activities of Daily Living for Telemedical Assessment of Cardiovascular Risk

With the recent advancement in wearable computing, sensor technologies, and data processing approaches, it is possible to develop smart clothing that integrates sensors into garments. The main objective of this study was to develop the method of automatic recognition of sedentary behavior related to cardiovascular risk based on quantitative measurement of physical activity. The solution is based on the designed prototype of the smart shirt equipped with a processor, wearable sensors, power supply and telemedical interface. The data derived from wearable sensors were used to create feature vector that consisted of the estimation of the user-specific relative intensity and the variance of filtered accelerometer data. The method was validated using an experimental protocol which was designed to be safe for the elderly and was based on clinically validated short physical performance battery (SPPB) test tasks. To obtain the recognition model six classifiers were examined and compared including Linear Discriminant Analysis, Support Vector Machines, K-Nearest Neighbors, Naive Bayes, Binary Decision Trees and Artificial Neural Networks. The classification models were able to identify the sedentary behavior with an accuracy of 95.00% ± 2.11%. Experimental results suggested that high accuracy can be obtained by estimating sedentary behavior pattern using the smart shirt and machine learning approach. The main advantage of the developed method to continuously monitor patient activities in a free-living environment and could potentially be used for early detection of increased cardiovascular risk.

Context Mining of Sedentary Behaviour for Promoting Self-Awareness Using a Smartphone

Sedentary behaviour is increasing due to societal changes and is related to prolonged periods of sitting. There is sufficient evidence proving that sedentary behaviour has a negative impact on people’s health and wellness. This paper presents our research findings on how to mine the temporal contexts of sedentary behaviour by utilizing the on-board sensors of a smartphone. We use the accelerometer sensor of the smartphone to recognize user situations (i.e., still or active). If our model confirms that the user context is still, then there is a high probability of being sedentary. Then, we process the environmental sound to recognize the micro-context, such as working on a computer or watching television during leisure time. Our goal is to reduce sedentary behaviour by suggesting preventive interventions to take short breaks during prolonged sitting to be more active. We achieve this goal by providing the visualization to the user, who wants to monitor his/her sedentary behaviour to reduce unhealthy routines for self-management purposes. The main contribution of this paper is two-fold: (i) an initial implementation of the proposed framework supporting real-time context identification; (ii) testing and evaluation of the framework, which suggest that our application is capable of substantially reducing sedentary behaviour and assisting users to be active.