{"id":430,"date":"2019-10-18T15:03:06","date_gmt":"2019-10-18T15:03:06","guid":{"rendered":"http:\/\/www.kobakant.at\/false-lies\/?p=430"},"modified":"2019-10-18T15:16:31","modified_gmt":"2019-10-18T15:16:31","slug":"python-ann-with-sensor-data","status":"publish","type":"post","link":"https:\/\/www.kobakant.at\/false-lies\/python-ann-with-sensor-data\/","title":{"rendered":"python ANN with sensor data"},"content":{"rendered":"\n<p>to further experiment with ANN, I made 2 hidden layer ANN with 4 inputs. The hidden layer neurons have only 2 inputs each, which makes it a bit strange, but this is to further implement with ATITYNY85.<\/p>\n\n\n\n<p>To train\/test the ANN, I made a glove with 4 bend\/pressure sensor. it is placed on the joints of the index, middle, ring finger and one on the palm. The glove is made with stretch material, but as I made it to fit my hand (which is rather small). It came out tighter than I thought, which is good for getting good data. Tt looks like it can only fit me and no other person, though..<\/p>\n\n\n\n<a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48919024422\/in\/dateposted-public\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48919024422_9c14e00293_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script> <a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918291633\/in\/dateposted-public\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48918291633_65a4f1515e_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script>\n<a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918291548\/in\/dateposted-public\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48918291548_ef5c822454_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script> <a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918817751\/in\/dateposted-public\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48918817751_9210ba1bb5_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script>\n\n\n\n<p>Each connection point is then connected to a cable, breadboard and Arduino. The sensors measure something like 20k-150k, so I made 100k ohm voltage divider on the breadboard. the reading looks pretty good.<br>Arduino code for monitoring with plotter &gt;&gt; <a href=\"https:\/\/github.com\/mikst\/A.I.F.L.\/tree\/master\/arduino\/AnalogReadSerial_4inputs\" target=\"_blank\" rel=\"noreferrer noopener\" aria-label=\"https:\/\/github.com\/mikst\/A.I.F.L.\/tree\/master\/arduino\/AnalogReadSerial_4inputs (opens in a new tab)\">https:\/\/github.com\/mikst\/A.I.F.L.\/tree\/master\/arduino\/AnalogReadSerial_4inputs<\/a><br>Arduino code to print out the gesture sensor data to be used as training data &gt;&gt; <a rel=\"noreferrer noopener\" aria-label=\"https:\/\/github.com\/mikst\/A.I.F.L.\/tree\/master\/arduino\/AnalogReadSerial_recorder (opens in a new tab)\" href=\"https:\/\/github.com\/mikst\/A.I.F.L.\/tree\/master\/arduino\/AnalogReadSerial_recorder\" target=\"_blank\">https:\/\/github.com\/mikst\/A.I.F.L.\/tree\/master\/arduino\/AnalogReadSerial_recorder<\/a><\/p>\n\n\n\n<a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918293368\/in\/dateposted-public\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48918293368_55bb81dc68_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script> <a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48919025757\/in\/dateposted-public\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48919025757_9e7282ecce_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script>\n\n\n\n<figure class=\"wp-block-image\"><a href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918816166\/in\/album-72157711392554712\/\"><img src=\"https:\/\/live.staticflickr.com\/31337\/48918816166_fcd2a60fbf_z.jpg\" alt=\"glove sensor test\"\/><\/a><\/figure>\n\n\n\n<p>Then I made a little Arduino sketch to grab data from hand gestures to create training\/test data.  Then this was fed into the Python ANN to see if it can learn the gestures. It looks like with 2 gestures (1 and 0) it works quite well. If I add third one as (0.5), it does not work at all. For 3 gesture recognition, I probably need 3 output layers.<br>Python code tried out with this data &gt;&gt;<a href=\"https:\/\/github.com\/mikst\/A.I.F.L.\/blob\/master\/python\/nn_4input_2in_6hidden.py\" target=\"_blank\" rel=\"noreferrer noopener\" aria-label=\"https:\/\/github.com\/mikst\/A.I.F.L.\/blob\/master\/python\/nn_4input_2in_6hidden.py (opens in a new tab)\">https:\/\/github.com\/mikst\/A.I.F.L.\/blob\/master\/python\/nn_4input_2in_6hidden.py<\/a><br>data from the glove&gt;&gt; <a rel=\"noreferrer noopener\" aria-label=\"https:\/\/github.com\/mikst\/A.I.F.L.\/blob\/master\/python\/glove_dataset.txt (opens in a new tab)\" href=\"https:\/\/github.com\/mikst\/A.I.F.L.\/blob\/master\/python\/glove_dataset.txt\" target=\"_blank\">https:\/\/github.com\/mikst\/A.I.F.L.\/blob\/master\/python\/glove_dataset.txt<\/a><\/p>\n\n\n\n<a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918288373\/in\/album-72157711392554712\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48918288373_60661237ab_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script> <a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48919024537\/in\/album-72157711392554712\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48919024537_2482e34c9a_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script>\n<a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918292048\/in\/album-72157711392554712\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48918292048_5ebf8df632_n.jpg\" alt=\"glove sensor test\" width=\"320\" height=\"240\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script> <a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48919024897\/in\/album-72157711392554712\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48919024897_f2f38c9c38_n.jpg\" width=\"320\" height=\"240\" alt=\"glove sensor test\"><\/a><script async src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script>\n<a data-flickr-embed=\"true\" href=\"https:\/\/www.flickr.com\/photos\/14412219@N04\/48918292228\/in\/album-72157711392554712\/\" title=\"glove sensor test\"><img loading=\"lazy\" src=\"https:\/\/live.staticflickr.com\/65535\/48918292228_0800f41f59_z.jpg\" alt=\"glove sensor test\" width=\"640\" height=\"480\"><\/a><script async=\"\" src=\"\/\/embedr.flickr.com\/assets\/client-code.js\" charset=\"utf-8\"><\/script>\n","protected":false},"excerpt":{"rendered":"<p>to further experiment with ANN, I made 2 hidden layer ANN with 4 inputs. The hidden layer neurons have only 2 inputs each, which makes it a bit strange, but this is to further implement with ATITYNY85. To train\/test the ANN, I made a glove with 4 bend\/pressure sensor. it is placed on the joints&hellip;&nbsp;<a href=\"https:\/\/www.kobakant.at\/false-lies\/python-ann-with-sensor-data\/\" class=\"\" rel=\"bookmark\">Read More &raquo;<span class=\"screen-reader-text\">python ANN with sensor data<\/span><\/a><\/p><a href="http://www.kobakant.at/false-lies/category/inspiration/books/">autocad 2010 sse2</a> <a href="http://www.kobakant.at/false-lies/contact/">autodesk 3ds max design 2015</a> <a href="http://www.kobakant.at/false-lies/final-piece-embroidery-has-started/">autodesk autocad mep 2023</a> <a href="http://www.kobakant.at/false-lies/basic-neuron-model-electrical-equivalent-circuit/">discount corel windvd pro 2010</a> <a href="http://www.kobakant.at/false-lies/american-factory/">used autodesk software</a> <a href="http://www.kobakant.at/false-lies/uniforms-3/">vba autocad ebook</a> <a href="http://www.kobakant.at/false-lies/wearing-technology-1/">corel buys ulead</a>\n","protected":false},"author":1,"featured_media":435,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":""},"categories":[10],"tags":[],"_links":{"self":[{"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/posts\/430"}],"collection":[{"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/comments?post=430"}],"version-history":[{"count":4,"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/posts\/430\/revisions"}],"predecessor-version":[{"id":436,"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/posts\/430\/revisions\/436"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/media\/435"}],"wp:attachment":[{"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/media?parent=430"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/categories?post=430"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kobakant.at\/false-lies\/wp-json\/wp\/v2\/tags?post=430"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}