{"id":48,"date":"2019-03-03T03:51:17","date_gmt":"2019-03-03T03:51:17","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/?p=48"},"modified":"2019-03-03T03:51:17","modified_gmt":"2019-03-03T03:51:17","slug":"ryan-week-3-status-report","status":"publish","type":"post","link":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/2019\/03\/03\/ryan-week-3-status-report\/","title":{"rendered":"Ryan \u2013 Week 3 Status Report"},"content":{"rendered":"<div class=\"textLayer--absolute\">This week I worked on classifying the testing heart sound data as abnormal vs normal using a Convolutional Neural Network. The design for the CNN is as follows:<\/div>\n<div><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-medium wp-image-39\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-content\/uploads\/sites\/19\/2019\/02\/CNN_structure-300x94.png\" alt=\"\" width=\"300\" height=\"94\" srcset=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-content\/uploads\/sites\/19\/2019\/02\/CNN_structure-300x94.png 300w, http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-content\/uploads\/sites\/19\/2019\/02\/CNN_structure.png 627w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/div>\n<div>Since we are no longer using an external cloud service to run our analysis, I have to decrease the size of the data using MaxPool Layer, which transforms the original data file by ignoring the local minimum values and only extracting the maximum values in a local area. The ReLU layer is mainly used to make the data non-linear, but it also reduces the computation time because it sets all negative values to be zero and computations with values of zero are much easier on a system than doing computations on also negative values. This structure was successful for me when classifying images of handwritten digits, so I was curious whether it would also be successful for audio data. The input audio data for the neural network was the filtered training sound files from week 2. If unsuccessful, I have to either improve the filtering technique using Eri&#8217;s research or change the structure of the CNN.<\/div>\n<div><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-medium wp-image-49\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-content\/uploads\/sites\/19\/2019\/03\/cnn_res-300x190.png\" alt=\"\" width=\"300\" height=\"190\" srcset=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-content\/uploads\/sites\/19\/2019\/03\/cnn_res-300x190.png 300w, http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-content\/uploads\/sites\/19\/2019\/03\/cnn_res.png 624w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/div>\n<div class=\"textLayer--absolute\">This is what the results looked like, but it never reached a final accuracy rating since it kept jumping around for the final iterations, so the structure of the CNN has to be changed for the next few weeks.<\/div>\n<div><\/div>\n<div>I am on schedule with the classification.<\/div>\n","protected":false},"excerpt":{"rendered":"<p>This week I worked on classifying the testing heart sound data as abnormal vs normal using a Convolutional Neural Network. The design for the CNN is as follows: Since we are no longer using an external cloud service to run our analysis, I have to decrease the size of the data using MaxPool Layer, which &hellip; <\/p>\n<p class=\"link-more\"><a href=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/2019\/03\/03\/ryan-week-3-status-report\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Ryan \u2013 Week 3 Status Report&#8221;<\/span><\/a><\/p>\n","protected":false},"author":53,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/posts\/48"}],"collection":[{"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/users\/53"}],"replies":[{"embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/comments?post=48"}],"version-history":[{"count":1,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/posts\/48\/revisions"}],"predecessor-version":[{"id":50,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/posts\/48\/revisions\/50"}],"wp:attachment":[{"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/media?parent=48"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/categories?post=48"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s19-teama4\/wp-json\/wp\/v2\/tags?post=48"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}