Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/75091
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Emilia Shi Ting | - |
dc.date.accessioned | 2018-05-28T05:03:48Z | - |
dc.date.available | 2018-05-28T05:03:48Z | - |
dc.date.issued | 2018 | - |
dc.identifier.uri | http://hdl.handle.net/10356/75091 | - |
dc.description.abstract | Wheezy breaths are key indicators of possible airway obstruction disorders such as asthma along with cough severity and abnormal breathing patterns[1]. The Stethoscope is usually the main form of listening to possibly obstructed lung airways or abnormal heart rate. However, some of such adventitious sounds observed to computerised sound data may not be audible to the human ear when using the stethoscope due to these data not prevalent in our more sensitive frequency band width. Therefore, in order to increase the accuracy of auscultation, digitalisation and machine learning methods has been researched on in recent studies. With increasing digitalisation of the modern world, possibilities has widened with readily available methods to diagnose symptoms that require frequent monitoring. The availability of such a technology would aid parents in detecting wheezing in their child at the comfort of their homes. The objective of this project will be to develop an android mobile application to diagnose if wheezing exists in a recording of human breathing. Two linear analysis methods of detecting wheezing symptoms, namely Kurtosis and Mean Crossing Irregularity, are evaluated for their accuracy. After which, the best method for wheeze detection is used in the mobile application. The deliverables are visualisations of the two algorithms accuracy in wheeze detection and an android application for wheeze detection. The main function of the mobile application is to record an episode of breathing and display diagnosis of wheezing detection using a feature extracted earlier in the research comparison. The feature used is Mean Crossing Irregularity whereby the deviation from the mean is divided by the average value of a data set. | en_US |
dc.format.extent | 72 p. | en_US |
dc.language.iso | en | en_US |
dc.rights | Nanyang Technological University | - |
dc.subject | DRNTU::Engineering | en_US |
dc.title | Smart phone apps for respiratory sound analysis | en_US |
dc.type | Final Year Project (FYP) | en_US |
dc.contributor.supervisor | Ser Wee | en_US |
dc.contributor.school | School of Electrical and Electronic Engineering | en_US |
dc.description.degree | Bachelor of Engineering | en_US |
item.fulltext | With Fulltext | - |
item.grantfulltext | restricted | - |
Appears in Collections: | EEE Student Reports (FYP/IA/PA/PI) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FYPFinalReport_Emilia.pdf Restricted Access | Final Report | 2.65 MB | Adobe PDF | View/Open |
Page view(s)
263
Updated on Nov 1, 2024
Download(s)
19
Updated on Nov 1, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.