This paper presents a method of extracting primary heart sound signals from chest-worn accelerometer data in the presence of motion artifacts. The proposed method outperforms noise removal techniques such as wavelet denoising and adaptive filtering. Results from six subjects show a primary heart signal detection rate of 99.36% with a false positive rate of 1.3%.
Machine perception is a difficult problem both from a practical or implementation point of view as well as from a theoretical or algorithm point of view. Machine perception systems based on biological perception systems show great promise in many areas but they often have processing requirements and/or data flow requirements that are difficult to implement, especially in small or low-power systems. We propose a system design approach that makes it possible to implement complex functionality using cooperative analog-digital signal processing to lower-power requirements dramatically over digital-only systems, as well as provide an architecture facilitating the development of biologically motivated perception systems. We show the architecture and application development approach. We also present several reference systems for speech recognition, noise suppression, and audio classification
We explore the use of physiologically inspired auditory features with both physiologically motivated and statistical audio classification methods. We use features derived from a biophysically defensible model of the early auditory system for audio classification using a neural network classifier. We also use a Gaussian-mixture-model (GMM)-based classifier for the purpose of comparison and show that the neural-network-based approach works better. Further, we use features from a more advanced model of the auditory system and show that the features extracted from this model of the primary auditory cortex perform better than the features from the early auditory stage. The features give good classification performance with only one-second data segments used for training and testing
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.