Context Awareness of Human Motion States Using Accelerometer

Abstract

The proposed context awareness system is composed of acceleration data acquisition part and fuzzy inference system that processes acquired data, distinguishes user motion states and recognizes emergency situations. Two-axial accelerometer embedded in SenseWear PRO2 Armband (BodyMedia) on the right upper arm collects input data containing the longitudinal acceleration average (LAA), the transverse acceleration average (TAA), the longitudinal acceleration-mean of absolute difference (L-MAD), and transverse acceleration mean of absolute difference (T-MAD). Fuzzy inference system is a tool imitating the human ability of decision making. In our system, the fuzzy inference system was used to distinguish the user motion states and to recognize emergency situations. In an experiment using eight subjects, the recognition rates of lying, sitting, walking and running were 98.9%, 98.9%, 99.7% and 99.9%, respectively. Recognition rate for lying after walking and lying after running was 100%.

Sensor Data Acquisition and Processing Parameters for Human Activity Classification

“…The Mean metric (see Equation (4)) has been used to: recognize sitting and standing [28,29]; it discriminates between periods of activity and rest [30]; and as an input to classifiers such as Decision Table, KNN, J48, Naïve Bayes, Random Forest, Hidden Markov Model (HMM) [7,16,31,32]: ${\text{italicMean}}_{X-\mathit{\text{Axis}}}=\frac{{\sum }_{i=1}^n{x}_i}{n}$…”

Fuzzy Computing Model of Activity Recognition on WSN Movement Data for Ubiquitous Healthcare Measurement

“…The ANFIS typically hybridizes benefits of FIS and neural network, and includes six layers that are input, fuzzification, rule antecedence, rule strength normalization, rule consequence, and inference with defuzzification [37]. In which, with the process as shown in Figure 4b, the fuzzification layer allows the clustering algorithm to allocate input variables for an initial fuzzy set, and the antecedent layer constructs the nodes that represent the membership functions.…”

“…In which, two well established types of FIS can be utilized: i.e., the Mamdani type which uses typical membership functions of output features for defuzzification [35] and the Sugeno type which entails weight average by constant or linear expression to compute crisp output [36]. The FIS was employed in many studies to distinguish patterns of human activities that were measured by various mobile devices with an approximate 90%–100% recognition rate dependent on features [37,38,39,40,41]. In addition, the neuro-fuzzy algorithm was suggested to adapt the training-based dataset to the training procedure for comprehensive and accurate recognition of adopted features [42,43,44,45].…”

Preprocessing techniques for context recognition from accelerometer data

“…Several researchers have used the mean to either directly or indirectly identify user posture (sitting, standing or lying) [11,19,22,23] and also to discriminate the type of activity as either dynamic or static [60]. Others have used the mean as input to classifiers like Neural Networks [51,59], Naive Bayes [27], Kohonen Self-Organizing Maps [29], Decision Trees [5], and even Fuzzy Inference [20]. Other applications of the mean value include, for example, axial calibration by finding the average value for all the different orientations [7] and the recognition of complex human gesture using Hidden Markov Models [8].…”