{"id":15,"date":"2020-02-12T17:22:26","date_gmt":"2020-02-12T17:22:26","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/?p=15"},"modified":"2020-02-12T17:22:26","modified_gmt":"2020-02-12T17:22:26","slug":"week-1-abstract-preliminary-design-thoughts","status":"publish","type":"post","link":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/2020\/02\/12\/week-1-abstract-preliminary-design-thoughts\/","title":{"rendered":"Week 1 &#8211;\u00a0Abstract &amp; Preliminary Design Thoughts"},"content":{"rendered":"<p><span style=\"font-weight: 400\">Pace Detection:<\/span><\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"font-weight: 400\"><b>Challenges with step count detection: <\/b><span style=\"font-weight: 400\">Therefore, various walking detection and step counting methods have been developed based on one or both of the following two physical phenomena: the moment when the same heel of a pedestrian strikes the ground once during each gait cycle results in a sudden rise in accelerations [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B17-sensors-18-00297\"><span style=\"font-weight: 400\">17<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B18-sensors-18-00297\"><span style=\"font-weight: 400\">18<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B19-sensors-18-00297\"><span style=\"font-weight: 400\">19<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B20-sensors-18-00297\"><span style=\"font-weight: 400\">20<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B21-sensors-18-00297\"><span style=\"font-weight: 400\">21<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B22-sensors-18-00297\"><span style=\"font-weight: 400\">22<\/span><\/a><span style=\"font-weight: 400\">]; the cyclic nature of human walking results in cyclic signals measured by motion sensors [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B13-sensors-18-00297\"><span style=\"font-weight: 400\">13<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B23-sensors-18-00297\"><span style=\"font-weight: 400\">23<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B24-sensors-18-00297\"><span style=\"font-weight: 400\">24<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B25-sensors-18-00297\"><span style=\"font-weight: 400\">25<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B26-sensors-18-00297\"><span style=\"font-weight: 400\">26<\/span><\/a><span style=\"font-weight: 400\">]. However, existing methods rely on the usage of dedicated foot-mounted sensors [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B27-sensors-18-00297\"><span style=\"font-weight: 400\">27<\/span><\/a><span style=\"font-weight: 400\">] or constrained smartphones [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B28-sensors-18-00297\"><span style=\"font-weight: 400\">28<\/span><\/a><span style=\"font-weight: 400\">], which essentially imposes severe limitations on applying these methods in practice. In addition, the methods based on smartphones suffer from limited accuracy, especially when smartphone is held in an unconstrained manner [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B29-sensors-18-00297\"><span style=\"font-weight: 400\">29<\/span><\/a><span style=\"font-weight: 400\">], namely that the smartphone placement is not only arbitrary but also alterable. Therefore, precisely identifying walking motion and counting the resultant steps are still challenging.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li><b>However, we don\u2019t care about accurate step count. We just need time distance between step counts<\/b><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li><b>How to convert steps\/second to beats\/measure?<\/b><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li><b>Possibilities:\u00a0<\/b><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"font-weight: 400\"><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/\"><span style=\"font-weight: 400\">https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/<\/span><\/a><span style=\"font-weight: 400\"> (has formulas we could adopt)<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li><b><span style=\"font-weight: 400\">The frequency domain approaches focus on the frequency content of successive windows of measurements based on short-term Fourier transform (STFT) [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B30-sensors-18-00297\"><span style=\"font-weight: 400\">30<\/span><\/a><span style=\"font-weight: 400\">], FFT [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B31-sensors-18-00297\"><span style=\"font-weight: 400\">31<\/span><\/a><span style=\"font-weight: 400\">], and continuous\/discrete wavelet transforms (CWT\/DWT) [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B30-sensors-18-00297\"><span style=\"font-weight: 400\">30<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B32-sensors-18-00297\"><span style=\"font-weight: 400\">32<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B33-sensors-18-00297\"><span style=\"font-weight: 400\">33<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B34-sensors-18-00297\"><span style=\"font-weight: 400\">34<\/span><\/a><span style=\"font-weight: 400\">], and can generally achieve high accuracy, but suffer from either resolution issues [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B34-sensors-18-00297\"><span style=\"font-weight: 400\">34<\/span><\/a><span style=\"font-weight: 400\">] or computational overheads [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B35-sensors-18-00297\"><span style=\"font-weight: 400\">35<\/span><\/a><span style=\"font-weight: 400\">]. In [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B31-sensors-18-00297\"><span style=\"font-weight: 400\">31<\/span><\/a><span style=\"font-weight: 400\">], steps are identified by extracting frequency domain features in acceleration data through FFT, and the accuracy of 87.52% was achieved. Additionally, FFT was employed in [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B36-sensors-18-00297\"><span style=\"font-weight: 400\">36<\/span><\/a><span style=\"font-weight: 400\">] too smooth acceleration data and then peak detection was used to count steps.<\/span><\/b><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">The feature clustering approaches employ machine learning algorithms, e.g., Hidden Markov models (HMMs) [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B37-sensors-18-00297\"><span style=\"font-weight: 400\">37<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B38-sensors-18-00297\"><span style=\"font-weight: 400\">38<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B39-sensors-18-00297\"><span style=\"font-weight: 400\">39<\/span><\/a><span style=\"font-weight: 400\">], KMeans clustering [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B40-sensors-18-00297\"><span style=\"font-weight: 400\">40<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B41-sensors-18-00297\"><span style=\"font-weight: 400\">41<\/span><\/a><span style=\"font-weight: 400\">], etc., in order to classify activities based on both time domain and frequency domain features extracted from sensory data [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B14-sensors-18-00297\"><span style=\"font-weight: 400\">14<\/span><\/a><span style=\"font-weight: 400\">,<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B42-sensors-18-00297\"><span style=\"font-weight: 400\">42<\/span><\/a><span style=\"font-weight: 400\">], but neither a single feature nor a single learning technique has yet been shown to perform the best [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B42-sensors-18-00297\"><span style=\"font-weight: 400\">42<\/span><\/a><span style=\"font-weight: 400\">].<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">A fair and extensive comparison has been made among various techniques in a practical environment in [<\/span><a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5796454\/#B29-sensors-18-00297\"><span style=\"font-weight: 400\">29<\/span><\/a><span style=\"font-weight: 400\">], and shows that the best performing algorithms for walking detection are thresholding based on the standard deviation and signal energy, STFT and autocorrelation, while the overall best step counting algorithms are windowed peak detection, HMM and CWT.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">In this paper, we adopt the gyroscope that is becoming more and more popular in COTS smartphones and the efficient FFT method to implement a novel and practical method for simultaneous walking detection and step counting. Due to the advantages of the gyroscope and frequency domain approach, the proposed method relieves the restriction of most existing studies that assume the usage of smartphones in a constrained manner.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li><b>Android has \u2018motion sensors\u2019 documentation for accelerometer info<\/b><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Example of accelerometer graph (peak to peak =? pace): <\/span><a href=\"https:\/\/www.analog.com\/media\/en\/analog-dialogue\/volume-44\/number-2\/articles\/pedometer-design-3-axis-digital-acceler.pdf\"><span style=\"font-weight: 400\">https:\/\/www.analog.com\/media\/en\/analog-dialogue\/volume-44\/number-2\/articles\/pedometer-design-3-axis-digital-acceler.pdf<\/span><\/a><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li><b>Android has a built in step counter &amp; step detector!!! Use this LOL<\/b><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Type_step_counter from sensor class<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Type_step_detector from sensor class<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">How to use: <\/span><a href=\"https:\/\/hub.packtpub.com\/step-detector-and-step-counters-sensors\/\"><span style=\"font-weight: 400\">https:\/\/hub.packtpub.com\/step-detector-and-step-counters-sensors\/<\/span><\/a><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Must generate our own graph<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Do analysis (as seen in research papers) from there<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p><span style=\"font-weight: 400\">Nontechnical Goals:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Real-time <\/span><span style=\"font-weight: 400\">!!??!!<\/span><\/li>\n<\/ul>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Play songs of current running pace<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Play song timewarped at current running pace<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Play song with added beats at current running pace<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">*** if running pace changes during song, real-time changes to music playing?<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">*** how else can we play with music with ML?<\/span><\/li>\n<\/ul>\n<p><strong>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8211;<\/strong><\/p>\n<p><span style=\"font-weight: 400\">Technical Goals:<\/span><\/p>\n<p>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;<\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Interface<\/span><\/li>\n<\/ul>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Smartwatch app &amp; mobile app<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If this requires two sets of source code, ONLY smartwatch app<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If this isn\u2019t possible, ONLY mobile app<\/span><\/li>\n<\/ol>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">*** to what EXTENT should we develop UI \/ user board \/ various screens? We could just have a button that starts the process. OR we could develop an app that looks like a real product that may exist in app store V1.0<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">*** smartwatch hardware may not match mobile hardware for computational abilities<\/span><\/li>\n<\/ul>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Pace Detection <\/span><span style=\"font-weight: 400\">???<\/span><\/li>\n<\/ul>\n<p>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;<\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Song choice<\/span><\/li>\n<\/ul>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Playlist exists, software chooses song of correct\/nearest tempo for natural music\u00a0<\/span>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">ML algo to determine a song\u2019s tempo<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Database that holds pairs of song &amp; its tempo<\/span><\/li>\n<\/ol>\n<\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Playlist exists, software plays songs in order with warping<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Suggested songs play based on pace &amp; profile music data &#8211; ML<\/span><\/li>\n<\/ol>\n<p>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;<\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Time-warp songs<\/span><\/li>\n<\/ul>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Wavelet Transform &#8211; previous groups mentioned this was more \u2018accurate\u2019 \/ \u2018advanced\u2019 &amp; better logarithmic runtime<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Phase Vocoder &#8211; 2 previous groups actually used this method. changes speed without changing pitch. Uses STFT, modulation in frequency domain, then inv. STFT<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">TDHS is also an option. Song hunter decided not to use this bc its not suited for polyphonic material (what does that mean?) &#8211; research this further and reprioritize methods to timewarp.<\/span><\/li>\n<\/ol>\n<p>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;<\/p>\n<ul>\n<li><span style=\"font-weight: 400\">Add beats at running pace\u00a0<\/span><\/li>\n<\/ul>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Heart beat \/ some other rhythm<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Just tempo beats<\/span><\/li>\n<\/ol>\n<p>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;<\/p>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Simple impulses at pitch within a chord progression? At first glance, is this a complete mystery, or do we have an idea of how to begin<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If not of a certain pitch, insert impulses at running pace<\/span><\/li>\n<\/ol>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Integration<\/span>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Interface<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Retrieve pace from phone<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Send pace from phone data to app<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">App performs its job &#8211; find music &amp; play it<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;<\/p>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">MVP<\/span>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Mobile app with basic \u201cStart\u201d and options buttons<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Default list of music<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Pace detection\u00a0<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Time-warping\u00a0<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Song changes based on pace<\/span><\/li>\n<\/ol>\n<\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">2nd<\/span>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">smartwatch<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Interface with profile \/ User authentication<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">ML of song choice &#8211; specifically, tempo detection<\/span><\/li>\n<\/ol>\n<\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">3rd<\/span>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">ML of song choice &#8211; song suggestions<\/span><\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<p>&nbsp;<\/p>\n<p><span style=\"font-weight: 400\">Apps like this exist: <\/span><a href=\"https:\/\/www.iphoneness.com\/iphone-apps\/music-pace-running-app\/\"><span style=\"font-weight: 400\">https:\/\/www.iphoneness.com\/iphone-apps\/music-pace-running-app\/<\/span><\/a><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">These apps match your choose from their own library or from your existing playlist to your pace automatically or manually<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400\">None of these apps alter songs themselves to match pace<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Pace Detection: Challenges with step count detection: Therefore, various walking detection and step counting methods have been developed based on one or both of the following two physical phenomena: the moment when the same heel of a pedestrian strikes the ground once during each gait cycle results in a sudden rise in accelerations [17,18,19,20,21,22]; the &hellip; <\/p>\n<p class=\"link-more\"><a href=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/2020\/02\/12\/week-1-abstract-preliminary-design-thoughts\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Week 1 &#8211;\u00a0Abstract &amp; Preliminary Design Thoughts&#8221;<\/span><\/a><\/p>\n","protected":false},"author":291,"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\/s20-teame4\/wp-json\/wp\/v2\/posts\/15"}],"collection":[{"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/users\/291"}],"replies":[{"embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/comments?post=15"}],"version-history":[{"count":1,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/posts\/15\/revisions"}],"predecessor-version":[{"id":16,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/posts\/15\/revisions\/16"}],"wp:attachment":[{"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/media?parent=15"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/categories?post=15"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s20-teame4\/wp-json\/wp\/v2\/tags?post=15"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}