Merge branch 'master' of gitlab.com:Anson-Projects/projects

_posts/2022-02-14-machine-learning-directed-study-report-1/machine-learning-methods-for-orbital-debris-characterization.Rmd

@@ -50,6 +50,8 @@ The entire file of the compiled parts properties from Fusion 360 can be seen [he
 />
 :::
 
+<figcaption>[View Plot as an image](prepped.svg)</figcaption></br>
+
 Now that the data is processed and clean, characterization in Matlab can begin. The original idea was to perform _PCA_, but the method had difficulties producing meaningful results. This is likely because the current dataset is tiny for machine learning and the variation in the data is high. The application of _PCA_ will be revisited once the dataset grows. The first step for characterization is importing our data into Matlab.
 
 ```m
@@ -85,6 +87,8 @@ Below is another _Splom_, but with the clusters found above. Since the _k-means_
 />
 :::
 
+<figcaption>[View Plot as an image](prepped_clustered.svg)</figcaption></br>
+
 ## Next Steps
 
 The current dataset needs to be grown in both the amount of data and the variety of data. The most glaring issue with the current dataset is only two different material types. Modern satellites, and therefore their debris, is composed of dozens of unique materials. The other and harder to fix issue is finding/deriving more data properties. Properties such as cross-sectional are or aerodynamic drag would be very insightful, but there is no good way to collect that data. Thankfully, the 3D scanner methods to obtain more properties can be developed and applied over the entire dataset.

_posts/2022-02-14-machine-learning-directed-study-report-1/machine-learning-methods-for-orbital-debris-characterization.html

@@ -56,7 +56,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 }
 code span.al { color: #ad0000; } /* Alert */
 code span.an { color: #5e5e5e; } /* Annotation */
-code span.at { } /* Attribute */
+code span.at { color: #20794d; } /* Attribute */
 code span.bn { color: #ad0000; } /* BaseN */
 code span.bu { } /* BuiltIn */
 code span.cf { color: #007ba5; } /* ControlFlow */
@@ -77,7 +77,7 @@ code span.kw { color: #007ba5; } /* Keyword */
 code span.op { color: #5e5e5e; } /* Operator */
 code span.ot { color: #007ba5; } /* Other */
 code span.pp { color: #ad0000; } /* Preprocessor */
-code span.sc { color: #5e5e5e; } /* SpecialChar */
+code span.sc { color: #20794d; } /* SpecialChar */
 code span.ss { color: #20794d; } /* SpecialString */
 code span.st { color: #20794d; } /* String */
 code span.va { color: #111111; } /* Variable */
@@ -85,7 +85,6 @@ code span.vs { color: #20794d; } /* VerbatimString */
 code span.wa { color: #5e5e5e; font-style: italic; } /* Warning */
 </style>
 
-
   <!--radix_placeholder_meta_tags-->
   <title>Machine Learning Directed Study: Report 1</title>
 
@@ -117,7 +116,7 @@ code span.wa { color: #5e5e5e; font-style: italic; } /* Warning */
   <!--/radix_placeholder_rmarkdown_metadata-->
   
   <script type="text/json" id="radix-resource-manifest">
-  {"type":"character","attributes":{},"value":["assembly.jpg","clusters.svg","machine-learning-methods-for-orbital-debris-characterization_files/anchor-4.2.2/anchor.min.js","machine-learning-methods-for-orbital-debris-characterization_files/bowser-1.9.3/bowser.min.js","machine-learning-methods-for-orbital-debris-characterization_files/distill-2.2.21/template.v2.js","machine-learning-methods-for-orbital-debris-characterization_files/header-attrs-2.11/header-attrs.js","machine-learning-methods-for-orbital-debris-characterization_files/jquery-3.6.0/jquery-3.6.0.js","machine-learning-methods-for-orbital-debris-characterization_files/jquery-3.6.0/jquery-3.6.0.min.js","machine-learning-methods-for-orbital-debris-characterization_files/jquery-3.6.0/jquery-3.6.0.min.map","machine-learning-methods-for-orbital-debris-characterization_files/popper-2.6.0/popper.min.js","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy-bundle.umd.min.js","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy-light-border.css","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy.css","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy.umd.min.js","machine-learning-methods-for-orbital-debris-characterization_files/webcomponents-2.0.0/webcomponents.js","prepped.html","prepped.svg","prepped_clustered.html","prepped_clustered.svg"]}
+  {"type":"character","attributes":{},"value":["assembly.jpg","clusters.svg","machine-learning-methods-for-orbital-debris-characterization_files/anchor-4.2.2/anchor.min.js","machine-learning-methods-for-orbital-debris-characterization_files/bowser-1.9.3/bowser.min.js","machine-learning-methods-for-orbital-debris-characterization_files/distill-2.2.21/template.v2.js","machine-learning-methods-for-orbital-debris-characterization_files/header-attrs-2.11/header-attrs.js","machine-learning-methods-for-orbital-debris-characterization_files/header-attrs-2.7/header-attrs.js","machine-learning-methods-for-orbital-debris-characterization_files/jquery-1.11.3/jquery.min.js","machine-learning-methods-for-orbital-debris-characterization_files/jquery-3.6.0/jquery-3.6.0.js","machine-learning-methods-for-orbital-debris-characterization_files/jquery-3.6.0/jquery-3.6.0.min.js","machine-learning-methods-for-orbital-debris-characterization_files/jquery-3.6.0/jquery-3.6.0.min.map","machine-learning-methods-for-orbital-debris-characterization_files/popper-2.6.0/popper.min.js","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy-bundle.umd.min.js","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy-light-border.css","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy.css","machine-learning-methods-for-orbital-debris-characterization_files/tippy-6.2.7/tippy.umd.min.js","machine-learning-methods-for-orbital-debris-characterization_files/webcomponents-2.0.0/webcomponents.js","prepped.html","prepped.svg","prepped_clustered.html","prepped_clustered.svg"]}
   </script>
   <!--radix_placeholder_navigation_in_header-->
   <!--/radix_placeholder_navigation_in_header-->
@@ -1264,10 +1263,7 @@ code span.wa { color: #5e5e5e; font-style: italic; } /* Warning */
 
       // hoverable references
       $('span.citation[data-cites]').each(function() {
-        var refs = $(this).attr('data-cites').split(" ");
-        var refHtml = refs.map(function(ref) {
-          return "<p>" + $('#ref-' + ref).html() + "</p>";
-        }).join("\n");
+        var refHtml = $('#ref-' + $(this).attr('data-cites')).html();
         window.tippy(this, {
           allowHTML: true,
           content: refHtml,
@@ -1511,6 +1507,10 @@ code span.wa { color: #5e5e5e; font-style: italic; } /* Warning */
   style="height: 40vh"
 />
 </div>
+<figcaption>
+<a href="prepped.svg">View Plot as an image</a>
+</figcaption>
+<p></br></p>
 <p>Now that the data is processed and clean, characterization in Matlab can begin. The original idea was to perform <em>PCA</em>, but the method had difficulties producing meaningful results. This is likely because the current dataset is tiny for machine learning and the variation in the data is high. The application of <em>PCA</em> will be revisited once the dataset grows. The first step for characterization is importing our data into Matlab.</p>
 <div class="sourceCode" id="cb2"><pre class="sourceCode m"><code class="sourceCode matlab"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="va">data</span> <span class="op">=</span> <span class="va">readmatrix</span>(<span class="ss">&#39;prepped.csv&#39;</span>)<span class="op">;</span></span></code></pre></div>
 <p>Next <em>k-means</em> will be used to cluster the data. Since it is hard to represent data in higher dimensions than two, only two columns of data will be provided for the clustering. For now, I think it makes most intuitive sense to treat volume and mass as the most critical columns since the volume vs. mass plot shows 3 reasonably distinct groups.</p>
@@ -1532,6 +1532,10 @@ code span.wa { color: #5e5e5e; font-style: italic; } /* Warning */
   style="height: 40vh"
 />
 </div>
+<figcaption>
+<a href="prepped_clustered.svg">View Plot as an image</a>
+</figcaption>
+<p></br></p>
 <h2 id="next-steps">Next Steps</h2>
 <p>The current dataset needs to be grown in both the amount of data and the variety of data. The most glaring issue with the current dataset is only two different material types. Modern satellites, and therefore their debris, is composed of dozens of unique materials. The other and harder to fix issue is finding/deriving more data properties. Properties such as cross-sectional are or aerodynamic drag would be very insightful, but there is no good way to collect that data. Thankfully, the 3D scanner methods to obtain more properties can be developed and applied over the entire dataset.</p>
 <p>Once the dataset is grown, more advanced analysis can begin. PCA is the current goal and can hopefully be applied by the next report.</p>

_posts/2022-02-14-machine-learning-directed-study-report-1/machine-learning-methods-for-orbital-debris-characterization_files/header-attrs-2.7/header-attrs.js

@@ -0,0 +1,12 @@
+// Pandoc 2.9 adds attributes on both header and div. We remove the former (to
+// be compatible with the behavior of Pandoc < 2.8).
+document.addEventListener('DOMContentLoaded', function(e) {
+  var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
+  var i, h, a;
+  for (i = 0; i < hs.length; i++) {
+    h = hs[i];
+    if (!/^h[1-6]$/i.test(h.tagName)) continue;  // it should be a header h1-h6
+    a = h.attributes;
+    while (a.length > 0) h.removeAttribute(a[0].name);
+  }
+});