Sensor Type, Axis, and Position-Based Fusion and Feature Selection for Multimodal Human Daily Activity Recognition in Wearable Body Sensor Networks

Abstract

This research addresses the challenge of recognizing human daily activities using surface electromyography (sEMG) and wearable inertial sensors. Effective and efficient recognition in this context has emerged as a cornerstone in robust remote health monitoring systems, among other applications. We propose a novel pipeline that can attain state-of-the-art recognition accuracies on a recent-and-standard dataset—the Human Gait Database (HuGaDB). Using wearable gyroscopes, accelerometers, and electromyography sensors placed on the thigh, shin, and foot, we developed an approach that jointly performs sensor fusion and feature selection. Being done jointly, the proposed pipeline empowers the learned model to benefit from the interaction of features that might have been dropped otherwise. Using statistical and time-based features from heterogeneous signals of the aforementioned sensor types, our approach attains a mean accuracy of 99.8%, which is the highest accuracy on HuGaDB in the literature. This research underlines the potential of incorporating EMG signals especially when fusion and selection are done simultaneously. Meanwhile, it is valid even with simple off-the-shelf feature selection methods such the Sequential Feature Selection family of algorithms. Moreover, through extensive simulations, we show that the left thigh is a key placement for attaining high accuracies. With one inertial sensor on that single placement alone, we were able to achieve a mean accuracy of 98.4%. The presented in-depth comparative analysis shows the influence that every sensor type, position, and placement can have on the attained recognition accuracies—a tool that can facilitate the development of robust systems, customized to specific scenarios and real-life applications.

HF-SPHR: Hybrid Features for Sustainable Physical Healthcare Pattern Recognition Using Deep Belief Networks

“…19 Fang et al [73] 79.24 Maitre et al [74] 84.89 Rasnayaka et al [75] 85 O'Halloran et al [76] 90. 55 Sun et al [77] 88 Tahir et al [23] 90.91 Badawi et al [25] 88 Masum et al [78] 91. 68 Kumari et al [79] 91.1 Ha et al [80] 91.94 --Guo et al [81] 92.…”

“…The EM algorithm estimates the unknown parameter sets Θ of probabilistic weights, and helps to find the maximum likelihood function by giving an initial parameter set Θ 1 and continuing to apply E and M steps. Then, the EM algorithm generates a sequence {Θ 1 , Θ 2 , …, Θ m , …} and considers both E and M steps, as in Equations (25) and 26:…”

MS-DLD: Multi-Sensors Based Daily Locomotion Detection via Kinematic-Static Energy and Body-Specific HMMs

“…Badawi et al [27] proposed a novel method based on the Human Gait Database (HuGaDB) dataset. Their contributions include the identification of the direction and sensor position, the best feature selection method, and achieving good recognition accuracy for HuGaDB.…”

Using Wearable Sensors for Human Activity Recognition in Logistics: A Comparison of Different Feature Sets and Machine Learning Algorithms

“…In this work, different time and frequency domain features have been used to represent the information contained in the extracted windows of the accelerometer and gyroscope sensors. This choice is motivated by the works of [20], [21] who achieve very good results for human activity recognition, we compute twelve time domain and four frequency domain features in the feature extraction process. These are listed in Table II.…”