Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities

Oxygen consumption ($$\dot{\,{{\mbox{V}}}}{{{\mbox{O}}}}_{2}$$ V ̇ O 2 ) provides established clinical and physiological indicators of cardiorespiratory function and exercise capacity. However, $$\dot{\,{{\mbox{V}}}}{{{\mbox{O}}}}_{2}$$ V ̇ O 2 monitoring is largely limited to specialized laboratory settings, making its widespread monitoring elusive. Here we investigate temporal prediction of $$\dot{\,{{\mbox{V}}}}{{{\mbox{O}}}}_{2}$$ V ̇ O 2 from wearable sensors during cycle ergometer exercise using a temporal convolutional network (TCN). Cardiorespiratory signals were acquired from a smart shirt with integrated textile sensors alongside ground-truth $$\dot{\,{{\mbox{V}}}}{{{\mbox{O}}}}_{2}$$ V ̇ O 2 from a metabolic system on 22 young healthy adults. Participants performed one ramp-incremental and three pseudorandom binary sequence exercise protocols to assess a range of $$\dot{\,{{\mbox{V}}}}{{{\mbox{O}}}}_{2}$$ V ̇ O 2 dynamics. A TCN model was developed using causal convolutions across an effective history length to model the time-dependent nature of $$\dot{\,{{\mbox{V}}}}{{{\mbox{O}}}}_{2}$$ V ̇ O 2 . Optimal history length was determined through minimum validation loss across hyperparameter values. The best performing model encoded 218 s history length (TCN-VO2 A), with 187, 97, and 76 s yielding <3% deviation from the optimal validation loss. TCN-VO2 A showed strong prediction accuracy (mean, 95% CI) across all exercise intensities (−22 ml min−1, [−262, 218]), spanning transitions from low–moderate (−23 ml min−1, [−250, 204]), low–high (14 ml min−1, [−252, 280]), ventilatory threshold–high (−49 ml min−1, [−274, 176]), and maximal (−32 ml min−1, [−261, 197]) exercise. Second-by-second classification of physical activity across 16,090 s of predicted $$\dot{\,{{\mbox{V}}}}{{{\mbox{O}}}}_{2}$$ V ̇ O 2 was able to discern between vigorous, moderate, and light activity with high accuracy (94.1%). This system enables quantitative aerobic activity monitoring in non-laboratory settings, when combined with tidal volume and heart rate reserve calibration, across a range of exercise intensities using wearable sensors for monitoring exercise prescription adherence and personal fitness.

Coupling dynamic modelling and parameter identification of a flexible manipulator system with harmonic drive

This paper formulates a coupling dynamic model for a flexible manipulator system with harmonic drive using experimental identification method. Parameters of the driven model of the harmonic joint and parameters of coupling vibration model of the flexible manipulator are identified. Accordingly, coupling dynamic models of the proposed system are obtained. Coulomb friction of the joint is identified by step current excitation and uniform rotation experiments at a low speed. Then, the transfer function model of the harmonic joint is established and identified by a pseudorandom binary sequence excitation. And predicted outputs of the obtained model are in good agreement with the experimental setup. Relationships between strain of the flexible manipulator and coupling torque are presented by theoretical derivation. Based on the theoretical model, transfer function from the angular displacement of the servo motor to the coupling torque is identified. Experimental results show this identified model match well with the proposed structure, both in the time and frequency domain. As a result, coupling dynamic modelling of the flexible manipulator system with harmonic drive is accomplished.

Nonlinear Acoustic Spectroscopy Method for Nondestructive Testing of Thermally Damaged Concrete

Most concrete structures are subjected to a range of temperature corresponding to normal environmental temperatures. However, there are important cases where concrete structures may be exposed to much higher temperatures (e.g., jet aircraft engine blasts, building fires, chemical and metallurgical industrial applications in which the concrete is in close proximity to furnaces, and some nuclear power-related postulated accident conditions). Exposure of concrete to high temperatures affects its mechanical properties. In this paper we examine the dependence of the fundamental frequency on temperature to which the concrete beams were heated. Fundamental frequencies were obtained by an innovative method used Pseudorandom Binary Sequence of Maximum Length as a perturbation signal. For the verification of the results the Ultrasonic Pulse Velocity in concrete were also measured and flexural bending strengths were determined. The results show method with Pseudorandom Binary Sequence of Maximum Length as a perturbation signal as a very promising for non-destructive testing of thermally damaged concrete.