Human activity recognition via smart-belt in wireless body area networks

Abstract

Human activity recognition based on wireless body area networks plays an essential role in various applications such as health monitoring, rehabilitation, and physical training. Currently, most of the human activity recognition is based on smartphone, and it provides more possibilities for this task with the rapid proliferation of wearable devices. To obtain satisfactory accuracy and adapt to various scenarios, we built a smart-belt which embedded the VG350 as posture data collector. This article proposes a hierarchical activity recognition structure, which divides the recognition process into two levels. Then a multi-classification Support Vector Machine algorithm optimized by Particle Swarm Optimization is applied to identify five kinds of conventional human postures. And we compare the effectiveness of triaxial accelerometer and gyroscope when used together and separately. Finally, we conduct systematic performance analysis. Experimental results show that our overall classification accuracy is 92.3% and the F-Measure can reach 92.63%, which indicates the human activity recognition system is accurate and effective.

Human Activity Recognition Using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey

“…Figure 10 shows (a) the distribution of these models, (b) the obtained average accuracy and (c) the average number of recognized activities of daily life. Among the different types of classical ML models, the most commonly used model was the Support Vector Machine (SVM) model [4], [6], [58], [60], [69], [78], [79], [82], [85], [92], [95], [109], [118], [127], [131], [132], [136], [138], [142], [145], [155], [168], [169], [171], [173], [182], [184], [186], [187], [189], [190], [209]- [212] which was used in 35 papers, achieving an average accuracy of 92.3% over an average of 12 activities. The second most used model is the classical k-Nearest Neighbor (kNN) model [4], [6], [42], [60], [61], [69], [78], [79], [92], [95], [96],…”

“…Generally, as the number of sensors increases, the fusion step becomes more challenging. The most common sensor fusion methods are typically based on Bayesian estimation, Kalman Filters, and Particle Filtering techniques [58]. Nowadays, it is possible to implement these techniques directly at the hardware level inside the sensing modules, standardizing the application input and simplifying application development, maintenance, and extensibility.…”

“…Concerning the Noise Removal step, 48 CML-based articles and 12 DL-based articles make use of different noise removal techniques. Among all such techniques the most used ones are: z-normalization [75], [120], min-max [70], [127], and linear interpolation [102], [111] are the most used normalization steps, preceded by a filtering step based on the application of outlier detection [70], [117], [163], Butterworth [82], [101], [117], [123], [127], [128], [152], [155], [174], [189], median [74], [101], [117], [127], [132], [147], [155], [182], [183], high-pass [92], [96], [117], [128], [169], [173], [208], or statistical [58] filters.…”

B-HAR: an open-source baseline framework for in depth study of human activity recognition datasets and workflows

“…The data pre-processing step aims to reduce the effect of such issues and prepare the data for the model training phase. Concerning the hardware noise, in the literature, most of the existing techniques make use of digital filters as lowpass, highpass, bandpass, or statistical filters [31]- [33] as the Kalman filter [34]. Furthermore, the unbalanced datasets issue is usually handled, through specific techniques, by reducing/increasing the number of samples in the most/less populated class [35].…”

Exploration and Research of Human Identification Scheme Based on Inertial Data

“…The inertial data collected by the mobile phone sensor not only contains the feature information of each pedestrian, but also various noise interferences [ 21 ]. In order to accurately extract the required features in the subsequent recognition process, the data preprocessing is conducted [ 22 ]. The preprocessing steps include noise elimination and the process of normalization.…”