Pre-Processing Effect on the Accuracy of Event-Based Activity Segmentation and Classification through Inertial Sensors

Abstract

Inertial sensors are increasingly being used to recognize and classify physical activities in a variety of applications. For monitoring and fitness applications, it is crucial to develop methods able to segment each activity cycle, e.g., a gait cycle, so that the successive classification step may be more accurate. To increase detection accuracy, pre-processing is often used, with a concurrent increase in computational cost. In this paper, the effect of pre-processing operations on the detection and classification of locomotion activities was investigated, to check whether the presence of pre-processing significantly contributes to an increase in accuracy. The pre-processing stages evaluated in this study were inclination correction and de-noising. Level walking, step ascending, descending and running were monitored by using a shank-mounted inertial sensor. Raw and filtered segments, obtained from a modified version of a rule-based gait detection algorithm optimized for sequential processing, were processed to extract time and frequency-based features for physical activity classification through a support vector machine classifier. The proposed method accurately detected >99% gait cycles from raw data and produced >98% accuracy on these segmented gait cycles. Pre-processing did not substantially increase classification accuracy, thus highlighting the possibility of reducing the amount of pre-processing for real-time applications.

Indirect Recognition of Predefined Human Activities

“…The wearable gadgets were based on the new generation of the Inertial Measurement Unit (IMU), developed by x-io Technologies, UK. The IMU is a compact data acquisition platform that combines diverse onboard sensors (as displayed in Table 3 ), and it is largely used for the evaluation of gait variability [ 24 , 25 ]. As regards this study, it comprises an 8-channel analog input, and an SD-card to store the data.…”

Design and Development of a Novel Invasive Blood Pressure Simulator for Patient’s Monitor Testing

“…∆V OUT = Verror out GAIN1 (13) where the Verror out is the voltage error of the source (see Table 5), and the GAIN1 = 201 is the IA gain. The corresponding BP error can be computed from Equation (10).…”

“…The nonlinearity cannot be easily compensated but due to its small influence it can be neglected. The values reported in Table 5 correspond to a pressure of 0.15 mmHg for V IN = 1 VDC (0.015 mmHg for V IN = 10 VDC, respectively), obtained from Equations (10) and (13).…”

“…The BP resolution for V OUT is 0.076 mmHg for V IN = 1 VDC (0.0076 mmHg for V IN = 10 VDC), as it can be computed from Equations (10) and (13).…”

“…To validate this, the accuracy assessment of the device under different conditions was performed and results are described in this paper. This is a crucial aspect since the evaluation of the accuracy is necessary when dealing with systems used to obtain information on human performances or on the health state of a patient [13].…”