Toward Automatic Respiratory Disease Symptom Reporting Polytechnic Institute Academic Year 2024 Accepted Realizing the Digital Enterprise Non-speech human sounds, such as coughing, shortness of breathing, and wheezing are common symptoms of many respiratory diseases, including chronic obstructive pulmonary disease (COPD), asthma, and coronavirus-caused diseases, e.g., COVID-19, SARS, and MARS. Thereby, often physicians and researchers rely on patient-reported surveys, such as the Leicester Cough Questionnaire (LCQ), Cough-Specific Quality-of-Life Questionnaire (CQLQ), and COPD Assessment Test (CAT) for initial screening. Similar to other self-reported responses, these respiratory disease assessment surveys suffer from recall burdens, human errors, and biases. However, with the advancement of smartphone sensing and artificial intelligence (AI), we can detect coughing or breathing patterns from smartphone microphone audio signals. Thereby, this smartphone sensing can help us to automate the disease symptom reporting process. This way physicians will get a better understanding of someone’s condition through a remote and instantaneous assessment. Also, this smartphone-based objective reporting reduces healthcare overheads and increasingly growing expenses. Sudip Vhaduri Sudip Vhaduri During this project, we will closely work with the two undergraduate student researchers in every step, including problem formulation, data processing and characterizations, statistical analysis and data visualization, and interpretation of findings. Thereby, participating in this project, our student researchers will achieve technical expertise to solve real-world problems. The students will also get a clear idea of how their scientific discovery contributes to the entire healthcare community ranging from physicians to patients with respiratory diseases. This also involves reviewing and summarizing relevant literature. https://sudipvhaduri.wordpress.com/cair/ Students should be in good academic standing. Having some experience with machine learning modeling using Scikit learn, Tensorflow, or similar frameworks will be beneficial (but it's not required). Online Citi training/certification will be needed before starting the internship since this work involves human subjects. 0 10 (estimated)