Identifying typical physical activity on smartphone with varying positions and orientations

Abstract

BackgroundTraditional activity recognition solutions are not widely applicable due to a high cost and inconvenience to use with numerous sensors. This paper aims to automatically recognize physical activity with the help of the built-in sensors of the widespread smartphone without any limitation of firm attachment to the human body.MethodsBy introducing a method to judge whether the phone is in a pocket, we investigated the data collected from six positions of seven subjects, chose five signals that are insensitive to orientation for activity classification. Decision trees (J48), Naive Bayes and Sequential minimal optimization (SMO) were employed to recognize five activities: static, walking, running, walking upstairs and walking downstairs.ResultsThe experimental results based on 8,097 activity data demonstrated that the J48 classifier produced the best performance with an average recognition accuracy of 89.6% during the three classifiers, and thus would serve as the optimal online classifier.ConclusionsThe utilization of the built-in sensors of the smartphone to recognize typical physical activities without any limitation of firm attachment is feasible.

Smart Lifelogging: Recognizing Human Activities using PHASOR

“…In (Bayat et al, 2014) the authors used several classifiers and in order to overcome the difficulty of the phone position, they introduced a strategy to select a suitable classifier for recognizing some activities depending on the kind of activity and the position of the smartphone. In (Miao et al, 2015), the authors also discussed the impact of varying positions and orientations of smartphones on the qualification of HAR. They overcame this problem by developing an orientation-independent features so that the system can work with acceptable accuracy at any pockets.…”

“…Among types of wearable sensors, smartphones are preferred as the most convenient equipment that can monitor human activities because of its mobility, user-friendly interface, longtime attachment, and available resources such as various embedded sensors, strong CPU, memory, and battery (Shoaib et al, 2015). According to (Lara and Labrador, 2013) (Shoaib et al, 2015), existing challenges include in-sufficient (standard) training data (Vavoulas et al, 2016) (Ojetola et al, 2015), varying positions and orientations of smartphones on the human body (Miao et al, 2015), resource consumption and privacy (Siirtola and Roning, 2012), dynamic and adaptive sensor selection (Capela et al, 2016) and online versus offline training for classification methods (Shoaib et al, 2015)(Google Activity Recognition API, 2016), etc. Nevertheless, none of the related work discusses the human factor in Internet of Everything (IoE) systems.…”

Using Jaccard Distance Measure for Unsupervised Activity Recognition with Smartphone Accelerometers

“…The classification accuracy produced by their method is 80.29%. Fen Miao et al [15] have used accelerometer, gyroscope, proximity sensor, light sensor and magnetic sensor of a smartphone for HAR. The magnitude of linear acceleration combined with signals collected from gyroscope sensor and magnetic sensor are used.…”

“…The same time-domain features used in the work of Fen Miao et al [15] are extracted, which includes Mean, Standard Deviation, Median, Skewness, Kurtosis, and Inter-Quartile-Range.…”

“…In the work of Fen Miao et al [15], the time-domain features, including mean, standard deviation, median, skewness, kurtosis, and Inter-quartile-range are extracted from the resultant acceleration data to study the six daily activities using Decision Tree, Naive Bayes and an improved SVM. In the work of Carina Figueira et al [16], the activities of standing, sitting, walking, running, ascending stairs and descending stairs are studied.…”