%0 Journal Article %T Automated Cough Assessment on a Mobile Platform %A Mark Sterling %A Hyekyun Rhee %A Mark Bocko %J Journal of Medical Engineering %D 2014 %I Hindawi Publishing Corporation %R 10.1155/2014/951621 %X The development of an Automated System for Asthma Monitoring (ADAM) is described. This consists of a consumer electronics mobile platform running a custom application. The application acquires an audio signal from an external user-worn microphone connected to the device analog-to-digital converter (microphone input). This signal is processed to determine the presence or absence of cough sounds. Symptom tallies and raw audio waveforms are recorded and made easily accessible for later review by a healthcare provider. The symptom detection algorithm is based upon standard speech recognition and machine learning paradigms and consists of an audio feature extraction step followed by a Hidden Markov Model based Viterbi decoder that has been trained on a large database of audio examples from a variety of subjects. Multiple Hidden Markov Model topologies and orders are studied. Performance of the recognizer is presented in terms of the sensitivity and the rate of false alarm as determined in a cross-validation test. 1. Introduction The use of sound information is a growing area of application of signal processing techniques in healthcare and biomedicine. In particular, multiple groups have reported on the development of systems that analyze audio recordings of patients and identify bouts of coughing [1¨C5] or other sounds indicative of health concerns [6¨C9]. In addition to their value as a monitoring or screening tool, the automated nature of these systems potentially enables new modes of disease management, especially in conjunction with advances in mobile technology. Moreover, the type of approach presented here may be especially suited to improving outcomes and addressing chronic disease in populations that have been previously underserved [10]. This paper studies cough as a symptom of asthma in adolescents. For a variety of reasons, including social and developmental pressures, adolescents with an asthma diagnosis typically have an inaccurate understanding of their disease condition primarily due to poor symptom perception or downplaying symptoms [11, 12]. These issues can undermine effective symptom monitoring and medication adherence which can ultimately lead to poor condition management and high healthcare utilization. To address this problem a device is proposed that continuously monitors asthma symptoms, particularly coughing which is the most common symptom in pediatric asthma patients [13, 14]. The identified symptoms can be stored and later retrieved by a patient or healthcare provider as an objective reference indicating the levels of asthma %U http://www.hindawi.com/journals/jme/2014/951621/