Classification of basic daily movements using a triaxial accelerometer

Abstract

A generic framework for the automated classification of human movements using an accelerometry monitoring system is introduced. The framework was structured around a binary decision tree in which movements were divided into classes and subclasses at different hierarchical levels. General distinctions between movements were applied in the top levels, and successively more detailed subclassifications were made in the lower levels of the tree. The structure was modular and flexible: parts of the tree could be reordered, pruned or extended, without the remainder of the tree being affected. This framework was used to develop a classifier to identify basic movements from the signals obtained from a single, waist-mounted triaxial accelerometer. The movements were first divided into activity and rest. The activities were classified as falls, walking, transition between postural orientations, or other movement. The postural orientations during rest were classified as sitting, standing or lying. In controlled laboratory studies in which 26 normal, healthy subjects carried out a set of basic movements, the sensitivity of every classification exceeded 87%, and the specificity exceeded 94%; the overall accuracy of the system, measured as the number of correct classifications across all levels of the hierarchy, was a sensitivity of 97.7% and a specificity of 98.7% over a data set of 1309 movements.

Preprocessing techniques for context recognition from accelerometer data

“…The SMA metric can be used to distinguish between a resting state and user activity [38] in a classification framework for the recognition of basic daily movements. It is also possible to use SMA as the basis for identifying periods of user activity [21].…”

Classification and suitability of sensing technologies for activity recognition

“…A T [37], [110], [100], [85], [74], [56], [130], [104], [2], [45], [98], [103], [60], [47], [131], [119], [31], [70] Sitting(0)…”

“…A T [74], [100], [110], [62], [130], [2], [45], [60], [47], [131], [31], [70] Kin [8], [90]; Cam [29], [54], [75], [41]; grey Cam [49]; Cam+ 2xA T [111] Lying(0)…”

“…A T [37], [100], [62], [74], [56], [130], [2], [45], [60], [47], [31] Kin [90]; Cam [29], [54], [75], [41]; grey Cam [49] Evidence found in the literature suggest that for the recognition of all the activities presented in the above table, apart from Using Elevator, Walk Through Doors and Leaving the House, a single tri-axial accelerometer is sufficient. The main advantage of such wearable technology is the fact that it is widely available and relatively cheap.…”

“…A very well addressed sub-task of Health Condition is the fall detection in which accelerometers are seen as the suitable technology. [17], [11], [57], [73], [65], [55], [16], [74], [56], [130], [137], [119]; A B [82]; 2xA B [23]; G [18]; AG [64] Floor vibration-based sensor [4]; array of acoustic sensors [94]; Tilt sensor + piezoelectronic A + vibration sensor [83]; tri-axial MTx [134]; A T +G T [50], [127]; multiple A T [44]; A T +BAR [114] Kin [72], [90]; Cam [101], [7], [41] IR, pressure sensor, audio…”