Pervasive Monitoring of Motion and Muscle Activation: Inertial and Mechanomyography Fusion

Abstract

Muscle activity and human motion are useful parameters to map the diagnosis, treatment, and rehabilitation of neurological and movement disorders. In laboratory and clinical environments, electromyography (EMG) and motion capture systems enable the collection of accurate, high resolution data on human movement and corresponding muscle activity. However, controlled surroundings limit both the length of time and the breadth of activities that can be measured. Features of movement, critical to understanding patient progress, can change during the course of a day and daily activities may not correlate to the limited motions examined in a laboratory. We introduce a system to measure motion and muscle activity simultaneously over the course of a day in an uncontrolled environment with minimal preparation time and ease of implementation that enables daily usage. Our system combines a bespoke inertial measurement unit (IMU) and mechanomyography (MMG) sensor, which measures the mechanical signal of muscular activity. The IMU can collect data continuously, and transmit wirelessly, for up to 10 hours. We describe the hardware design and validation and outline the data analysis (including data processing and activity classification algorithms) for the sensing system. Furthermore, we present two pilot studies to demonstrate utility of the system, including activity identification in six able-bodied subjects with an accuracy of 98%, and monitoring motion/muscle changes in a subject with cerebral palsy and of a single leg amputee over extended periods (∼5 hours). We believe these results provide a foundation for mapping human muscle activity and corresponding motion changes over time, providing a basis for a range of novel rehabilitation therapies.

Identification of Upper-Limb Movements Based on Muscle Shape Change Signals for Human-Robot Interaction

“…And these interferences have been well studied with reports revealing their negative effects towards degrading real-time performances of motion intention decoding. Alternatively, nonphysiological signals based on muscle geometric and/or morphology changes that can be measured by different techniques such as ultrasound [7], capacitance [9], muscle circumference [10], and muscle activation [11,12] have been considered for motion intention recognition. In that regard, this study hypothesized that nonphysiological MSC signals should offer adequate information for limb movement intent 0 2070 18 1 38 23 483 0 1 2097 0 0 3 76 12 0 0 2109 10 2 145 1 7 7 3 2044 5 401 0 27 0 3 3 2079 112 6 27 11 14 Table 3: Macro-Precision, Macro-Recall, and Macro-F-score of both sensors (unit: %).…”

“…For instance, power line noise and motion artifacts would inevitably degrade the motion intention recognition accuracy of wearable systems that utilize sEMG or EEG signals as their sources of control. In an attempt to address this issue, researchers have sort alternative means from which motion intentions could be decoded which includes ultrasound [7], pressure [8], capacitance [9], muscle circumference [10], and muscle activation [11,12]. However, some of the systems are relatively large in size and integrate sensors that lack flexibility and stretchability characteristics, which are the core requirements for developing smart miniaturized intelligent devices that could be easily adopted in practical applications.…”

Facial Muscle Activity Recognition with Reconfigurable Differential Stethoscope-Microphones

“…Many activities that are performed by our body are intrinsically related to muscular contractions; therefore, activity recognition based on those contractions(myography) is an active research topic [ 43 , 44 , 45 ]. In this area, our specific interest is in the subset of mechanomyography, which involves measuring the force contraction using low-frequency sounds/vibrations (2–200 Hz) with a signal power below 50 Hz [ 46 ]. We proposed to use this method to capture the facial muscle (and to a degree tissue) movements for a specific group of gestures/facial expressions.…”

“…In [ 46 ], sound was combined with the IMU (Inertial Measurement Unit), to monitor the muscle’s movement of patients under rehabilitation. The inspiration came from the high variability of the features of a person’s actions during a typical day, in particular patients under-recovery from a neurological injury or an accident.…”

“…According to [ 46 ], the relevant frequency range is within “Area1”. The corresponding values of the minimum, maximum, and mean for each microphone are shown in Table 1 .…”