Abstract:In this study, we present a non-contact respiratory anomaly detection method using incoherent light-wave signals reflected from the chest of a mechanical robot that can breathe like human beings. In comparison to existing radar and camera-based sensing systems for vitals monitoring, this technology uses only a low-cost ubiquitous light source (e.g., infrared light emitting diode) and sensor (e.g., photodetector). This light-wave sensing (LWS) system recognizes different breathing anomalies from the variations of light intensity reflected from the chest of the robot within a 0.5m-1.5m range. The anomaly detection model demonstrates up to 96.6% average accuracy in classifying 7 different types of breathing data using machine learning. The model can also detect faulty data collected by the system that does not contain breathing information. The developed system can be utilized at home or healthcare facilities as a smart, non-contact and discreet respiration monitoring method.
Abstract:Human respiratory rate and its pattern convey important information about the physical and psychological states of the subject. Abnormal breathing can be a sign of fatal health issues which may lead to further diagnosis and treatment. Wireless light wave sensing (LWS) using incoherent infrared light turns out to be promising in human breathing monitoring in a safe, discreet, efficient and non-invasive way without raising any privacy concerns. The regular breathing patterns of each individual are unique, hence the respiration monitoring system needs to learn the subject's usual pattern in order to raise flags for breathing anomalies. Additionally, the system needs to be capable of validating that the collected data is a breathing waveform, since any faulty data generated due to external interruption or system malfunction should be discarded. In order to serve both of these needs, breathing data of normal and abnormal breathing were collected using infrared light wave sensing technology in this study. Two machine learning algorithms, decision tree and random forest, were applied to detect breathing anomalies and faulty data. Finally, model performance was evaluated using average classification accuracies found through cross-validation. The highest classification accuracy of 96.6% was achieved with the data collected at 0.5m distance using decision tree model. Ensemble models like random forest were found to perform better than a single model in classifying the data that were collected at multiple distances from the light wave sensing setup.