Abstract: A sensor module assembly for a respiratory therapy apparatus may be configured for a seal-based securement within a respiratory therapy device that includes a separable pneumatic block to make assembly or replacement more efficient. The sensor module assembly may include a flow manifold. The flow manifold may have an inlet and an outlet and a main pneumatic path between the inlet and the outlet. The assembly may have a sensor module with sensor(s) on a printed circuit board. The sensor module may be pneumatically and fixedly coupled to the flow manifold. The inlet of the flow manifold may be configured for removable coupling with an outlet of the pneumatic block assembly. Moreover, the outlet of the flow manifold may be configured for removable coupling with a pneumatic path of a housing panel of the respiratory therapy apparatus. The pneumatic path is adapted for supplying breathable gas to a patient interface.

Abstract: A method for classifying a microseismic event, including: analyzing microseismic event files through a combination of two fault tolerant machine learning pipelines, an acoustic machine learning pipeline and a visual machine learning pipeline; and generating a classification prediction for the microseismic event files by combining predictions from the acoustic machine learning pipeline and the visual machine learning pipeline.