In the context of tele-monitoring, great interest is presently devoted to physical activity, mainly of elderly or people with disabilities. In this context, many researchers studied the recognition of activities of daily living by using accelerometers. The present work proposes a novel algorithm for activity recognition that considers the variability in movement speed, by using dynamic programming. This objective is realized by means of a matching and recognition technique that determines the distance between the signal input and a set of previously defined templates. Two different approaches are here presented, one based on Dynamic Time Warping (DTW) and the other based on the Derivative Dynamic Time Warping (DDTW). The algorithm was applied to the recognition of gait, climbing and descending stairs, using a biaxial accelerometer placed on the shin. The results on DDTW, obtained by using only one sensor channel on the shin showed an average recognition score of 95%, higher than the values obtained with DTW (around 85%). Both DTW and DDTW consistently show higher classification rate than classical Linear Time Warping (LTW).

No abstract

No abstract

Two approaches to the classification of different locomotor activities performed at various speeds are here presented and evaluated: a maximum a posteriori (MAP) Bayes' classification scheme and a Support Vector Machine (SVM) are applied on a 2D projection of 16 features extracted from accelerometer data. The locomotor activities (level walking, stair climbing, and stair descending) were recorded by an inertial sensor placed on the shank (preferred leg), performed in a natural indoor-outdoor scenario by 10 healthy young adults (age 25–35 yrs.). From each segmented activity epoch, sixteen features were chosen in the frequency and time domain. Dimension reduction was then performed through 2D Sammon's mapping. An Artificial Neural Network (ANN) was trained to mimic Sammon's mapping on the whole dataset. In the Bayes' approach, the two features were then fed to a Bayes' classifier that incorporates an update rule, while, in the SVM scheme, the ANN was considered as the kernel function of the classifier. Bayes' approach performed slightly better than SVM on both the training set (91.4% versus 90.7%) and the testing set (84.2% versus 76.0%), favoring the proposed Bayes' scheme as more suitable than the proposed SVM in distinguishing among the different monitored activities.

-Detecting activities of daily living (ADL) and classifying the gesture typology are important tasks for rehabilitation and for applications in robotics. The use of wearable sensors, such as accelerometers, could facilitate the previous tasks since it would open the possibility of monitoring patients in real-life conditions. This study aims at detecting and classifying gestures recorded by accelerometers: in particular, a set of upper limb motor tasks that are contained in the rehabilitation scale known as Wolf Motor Function Test (WMFT), were used in this work. Two accelerometers, respectively a dual-axis one placed on the biceps and a three-axis one placed internally on the wrist, constitute the sensors set. Five normal subjects were included in the protocol and were asked to perform five different gestures. Dynamic Time Warping (DTW) approach was chosen to process data: this is a template matching technique that assesses the similarity between signals by using a reference signal (i.e. the Template). In this work a novel approach for the construction of the Template is proposed. The Median point DTW Template (MDTW), which is built by connecting the non-linear path between two signals corresponding to movements performed at two different speeds, is introduced. One MDTW was built for each channel, each gesture and each subject, and it was used as a reference signal to recognize five different gestures at various velocities. Moreover, aiming at the generalization of the approach, the recognition performance was also assessed on the classification obtained by using a unique Template for all the five voluntaries for each channel and for each gesture. The recognition percentage obtained by using the subject specific version of MDTW is around 94%, while with the subject independent approach the increase of generalization makes the recognition percentage decrease at around 88%. This latter approach would improve the applicability of wearable monitoring, by substantially decreasing the burden time for the template set construction on a subject-by-subject basis.