lingo.lol is one of the many independent Mastodon servers you can use to participate in the fediverse.
A place for linguists, philologists, and other lovers of languages.

Server stats:

65
active users

#clustering

0 posts0 participants0 posts today
Computo<p>Summer ☀️ read: a new paper on model-based clustering just appeared in Computo!</p><p>Julien Jacques and Brendan Thomas Murphy publish a new method for clustering multivariate count data. The method combines feature selection and clustering, and is based on conditionally independent Poisson mixture models and Poisson generalized linear models.</p><p>On simulations, the Adjusted Rand Index (ARI) of the model with selected variables is close to the optimal ARI obtained with the true clustering variables.</p><p>The paper and accompanying R code are available at <a href="https://computo-journal.org/published-202507-jacques-count-data/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">computo-journal.org/published-</span><span class="invisible">202507-jacques-count-data/</span></a></p><p><a href="https://mathstodon.xyz/tags/machineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machineLearning</span></a> <a href="https://mathstodon.xyz/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://mathstodon.xyz/tags/Rstats" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Rstats</span></a> <a href="https://mathstodon.xyz/tags/openScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openScience</span></a> <a href="https://mathstodon.xyz/tags/openSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openSource</span></a> <a href="https://mathstodon.xyz/tags/openAccess" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openAccess</span></a></p>
Enabla<p>Don't pass by the new insightful lecture from Dr. Alejandro Rodriguez Garcia, Abdus Salam International Centre for Theoretical Physics (ICTP)! </p><p>In this one, Alex provides a comprehensive overview of various clustering methods, including flat, fuzzy, and hierarchical approaches. His lecture not only discusses the mathematical foundations of techniques like k-means and k-medoids but also highlights their practical applications across fields such as image recognition and data classification.</p><p>This lecture is an excellent opportunity to deepen your understanding of unsupervised learning and engage critically with advanced clustering methods.</p><p>Join Enabla to watch the lecture and interact with Dr. Rodriguez Garcia for free! Ask questions and spark discussions with both him and the rest of the Enabla community: <a href="https://enabla.com/pub/1109/about" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">enabla.com/pub/1109/about</span><span class="invisible"></span></a></p><p><a href="https://mathstodon.xyz/tags/UnsupervisedLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UnsupervisedLearning</span></a> <a href="https://mathstodon.xyz/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mathstodon.xyz/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a> <a href="https://mathstodon.xyz/tags/Clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Clustering</span></a> <a href="https://mathstodon.xyz/tags/OpenAccess" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenAccess</span></a></p>
Benjamin Rosemann<p>Ein lang ersehnter Wunsch von mir: Eigene <a href="https://mastodon.social/tags/Clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Clustering</span></a> Methoden in <a href="https://mastodon.social/tags/OpenRefine" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenRefine</span></a> benutzen.</p><p>Verfügbar seit Version 3.9.0 und funktioniert seit 3.9.3 auch mit <a href="https://mastodon.social/tags/Jython" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Jython</span></a> und <a href="https://mastodon.social/tags/Clojure" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Clojure</span></a>.</p><p>Hier eine Anleitung zur Benutzung im <a href="https://mastodon.social/tags/FDMLab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FDMLab</span></a> Blog.</p><p><a href="https://fdmlab.landesarchiv-bw.de/workshop/openrefine-fortgeschrittene/19-erweitertes-clustering/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">fdmlab.landesarchiv-bw.de/work</span><span class="invisible">shop/openrefine-fortgeschrittene/19-erweitertes-clustering/</span></a></p><p><a href="https://mastodon.social/tags/LandesarchivBW" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LandesarchivBW</span></a></p>
MottG<p>Clustering Workbench of the Carrot2 search engine is working now. It can<br>cluster search results by 3 algorithms:<br>Lingo, STC, or k=means. STC is Suffix Tree Clustering method, a fast, phrase-based clustering method that groups documents based on common, frequent phrases. The screenshot shows search results using Lingo clustering for query:<br>"survey of AI tools for systematic reviews."</p><p><a href="https://search.carrot2.org/#/workbench" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">search.carrot2.org/#/workbench</span><span class="invisible"></span></a></p><p><a href="https://researchbuzz.masto.host/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>research</span></a> <a href="https://researchbuzz.masto.host/tags/academia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>academia</span></a> <a href="https://researchbuzz.masto.host/tags/Carrot2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Carrot2</span></a><br><a href="https://researchbuzz.masto.host/tags/systematicReview" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>systematicReview</span></a> <br><a href="https://researchbuzz.masto.host/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://researchbuzz.masto.host/tags/Lingo" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Lingo</span></a> <a href="https://researchbuzz.masto.host/tags/STC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STC</span></a> <a href="https://researchbuzz.masto.host/tags/k" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>k</span></a>-means</p>
💧🌏 Greg Cocks<p>A Methodology For The Multitemporal Analysis Of Land Cover Changes And Urban Expansion Using Synthetic Aperture Radar (SAR) Imagery - A Case Study Of The Aburrá Valley In Colombia<br>--<br><a href="https://doi.org/10.3390/rs17030554" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.3390/rs17030554</span><span class="invisible"></span></a> &lt;-- shared paper<br>--<br><a href="https://techhub.social/tags/GIS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GIS</span></a> <a href="https://techhub.social/tags/spatial" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spatial</span></a> <a href="https://techhub.social/tags/mapping" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>mapping</span></a> <a href="https://techhub.social/tags/SyntheticApertureRadar" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SyntheticApertureRadar</span></a> <a href="https://techhub.social/tags/SAR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SAR</span></a> <a href="https://techhub.social/tags/remotesensing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>remotesensing</span></a> <a href="https://techhub.social/tags/multitemporalanalysis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>multitemporalanalysis</span></a> <a href="https://techhub.social/tags/landcover" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>landcover</span></a> <a href="https://techhub.social/tags/landcoverchange" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>landcoverchange</span></a> <a href="https://techhub.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://techhub.social/tags/kurtosis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>kurtosis</span></a> <a href="https://techhub.social/tags/fuzzylogic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>fuzzylogic</span></a> <a href="https://techhub.social/tags/kernelbasedmethod" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>kernelbasedmethod</span></a> <a href="https://techhub.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://techhub.social/tags/spatialanalysis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spatialanalysis</span></a> <a href="https://techhub.social/tags/spatiotemporal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spatiotemporal</span></a> <a href="https://techhub.social/tags/geostatistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>geostatistics</span></a> <a href="https://techhub.social/tags/model" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>model</span></a> <a href="https://techhub.social/tags/modeling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>modeling</span></a> <a href="https://techhub.social/tags/Aburr%C3%A1Valley" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AburráValley</span></a> <a href="https://techhub.social/tags/Columbia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Columbia</span></a> <a href="https://techhub.social/tags/urban" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>urban</span></a> <a href="https://techhub.social/tags/urbanexpansion" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>urbanexpansion</span></a> <a href="https://techhub.social/tags/population" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>population</span></a> <a href="https://techhub.social/tags/growth" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>growth</span></a> <a href="https://techhub.social/tags/topography" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>topography</span></a> <a href="https://techhub.social/tags/monitoring" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>monitoring</span></a> <a href="https://techhub.social/tags/satellite" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>satellite</span></a> <a href="https://techhub.social/tags/sentinel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sentinel</span></a> <a href="https://techhub.social/tags/valley" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>valley</span></a> <a href="https://techhub.social/tags/landuse" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>landuse</span></a> <a href="https://techhub.social/tags/distribution" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>distribution</span></a> <a href="https://techhub.social/tags/infrastructure" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>infrastructure</span></a> <a href="https://techhub.social/tags/building" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>building</span></a> <a href="https://techhub.social/tags/roads" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>roads</span></a> <a href="https://techhub.social/tags/naturalresources" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>naturalresources</span></a> <a href="https://techhub.social/tags/environmental" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>environmental</span></a> <a href="https://techhub.social/tags/conservation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>conservation</span></a> <a href="https://techhub.social/tags/monitoring" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>monitoring</span></a> <a href="https://techhub.social/tags/multitemporal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>multitemporal</span></a></p>
Teresita Porter 🙋🏻‍♀️<p>**OptimOTU: Taxonomically aware OTU clustering with optimized thresholds and a bioinformatics workflow for metabarcoding data**</p><p><a href="https://arxiv.org/abs/2502.10350" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2502.10350</span><span class="invisible"></span></a></p><p><a href="https://ecoevo.social/tags/OTU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OTU</span></a> <a href="https://ecoevo.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://ecoevo.social/tags/bioinformatics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>bioinformatics</span></a> <a href="https://ecoevo.social/tags/DNAmetabarcoding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DNAmetabarcoding</span></a></p>
JuliaR<p>👋 Hi all <a href="https://fosstodon.org/tags/Rstats" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Rstats</span></a> enthusiasts!<br>I'm looking for someone who has time now to conduct a review of a piece of software for Journal of Open Source Software (JOSS). Details are here:<br><a href="https://github.com/openjournals/joss-reviews/issues/7319" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/openjournals/joss-r</span><span class="invisible">eviews/issues/7319</span></a></p><p>The review process is quite simple - you get a checklist and you run some tests. It's all open, on GitHub.</p><p><a href="https://fosstodon.org/tags/PeerReview" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PeerReview</span></a> <a href="https://fosstodon.org/tags/softwaredevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>softwaredevelopment</span></a> <a href="https://fosstodon.org/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> <a href="https://fosstodon.org/tags/programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>programming</span></a> <a href="https://fosstodon.org/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://fosstodon.org/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a> <a href="https://fosstodon.org/tags/Bioinformatics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Bioinformatics</span></a></p>
Kevin Karhan :verified:<p><span class="h-card" translate="no"><a href="https://m.ai6yr.org/@ai6yr" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>ai6yr</span></a></span> <span class="h-card" translate="no"><a href="https://techtoots.com/@dthacker9" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>dthacker9</span></a></span> <span class="h-card" translate="no"><a href="https://oxytodon.com/@fuchsiii" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>fuchsiii</span></a></span> I just found them cheap as surplus - there are also others from Dell (WYSE), Fujitsu (Futro) &amp; IGEL.</p><p>Basically almost all of them are cheap (like €50 at most, sometimes &lt;€10 in a 10-pack lot) and fanless, so ideal to do some <a href="https://infosec.space/tags/BareMetal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BareMetal</span></a> <a href="https://infosec.space/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> or just to have chugging along silently in the background...</p>
Vis Lab @ Khoury, Northeastern<p>ICYMI you can find <span class="h-card" translate="no"><a href="https://vis.social/@ebertini" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>ebertini</span></a></span> &amp; friends' paper "Towards a Visual Perception-Based Analysis of Clustering Quality Metrics" from Sunday's VDS workshop here: <a href="https://www.visualdatascience.org/2024/index.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">visualdatascience.org/2024/ind</span><span class="invisible">ex.html</span></a> <a href="https://vis.social/tags/IEEEVIS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IEEEVIS</span></a> <a href="https://vis.social/tags/Perception" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Perception</span></a> <a href="https://vis.social/tags/Clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Clustering</span></a> <a href="https://vis.social/tags/DataViz" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataViz</span></a> <a href="https://vis.social/tags/VDS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VDS</span></a></p>
Harald Klinke<p>Two great sources to explore the use of pan and zoom techniques in data visualization: </p><p>1. Shneiderman's "information-seeking mantra" emphasizes the importance of overview, zoom, and filter in exploring data clusters.<br><a href="https://infovis-wiki.net/wiki/Visual_Information-Seeking_Mantra" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">infovis-wiki.net/wiki/Visual_I</span><span class="invisible">nformation-Seeking_Mantra</span></a><br>2. "Zoomland" (de Gruyter, 2023), edited by Armaselu and Fickers, offers insights on zooming in data visualization.<br><a href="https://www.degruyter.com/document/doi/10.1515/9783111317779/html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">degruyter.com/document/doi/10.</span><span class="invisible">1515/9783111317779/html</span></a></p><p><a href="https://det.social/tags/DataViz" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataViz</span></a> <a href="https://det.social/tags/KenBurnsEffect" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KenBurnsEffect</span></a> <a href="https://det.social/tags/Clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Clustering</span></a></p>
Antonio Lieto<p>The paper "Interpretable Clusters for Representing Citizens’ Sense of Belonging through Interaction with Cultural Heritage" has been published in the ACM Journal of Computing and Cultural Heritage. </p><p>📝 Title: Interpretable Clusters for Representing Citizens’ Sense of Belonging through Interaction with Cultural Heritage</p><p>🌐 Index Terms: technology for <a href="https://fediscience.org/tags/culturalheritage" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>culturalheritage</span></a>, <a href="https://fediscience.org/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <br><a href="https://fediscience.org/tags/affectivecomputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>affectivecomputing</span></a>; social cohesion; <a href="https://fediscience.org/tags/museum" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>museum</span></a> interaction<br>Full paper: <a href="https://doi.org/10.1145/3665142" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.1145/3665142</span><span class="invisible"></span></a> <br><span class="h-card" translate="no"><a href="https://a.gup.pe/u/academicchatter" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>academicchatter</span></a></span></p>
Pete Bleackley<p>This week's <a href="https://wandering.shop/tags/KeyAlgorithms" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KeyAlgorithms</span></a> article discusses Hierarchical <a href="https://wandering.shop/tags/Clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Clustering</span></a><br><a href="https://playfultechnology.co.uk/hierarchical-clustering.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">playfultechnology.co.uk/hierar</span><span class="invisible">chical-clustering.html</span></a><br><a href="https://wandering.shop/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a> <a href="https://wandering.shop/tags/MachinrLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachinrLearning</span></a> <a href="https://wandering.shop/tags/UnsupervisedLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UnsupervisedLearning</span></a></p><p><span class="h-card" translate="no"><a href="https://a.gup.pe/u/data_science" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>data_science</span></a></span></p>
Mike D.<p><span class="h-card" translate="no"><a href="https://mastodon.social/@werefreeatlast" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>werefreeatlast</span></a></span> <br>I'm waiting on a similar sized dell to use as a media server. I will be running Ubuntu as well.</p><p>Many people use these to experiment with <a href="https://kolektiva.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a>. I've read a lot and watched some videos about clustering with <a href="https://kolektiva.social/tags/Proxmox" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Proxmox</span></a>.</p><p>-edited for grammar</p>
Fabrice Tshimanga<p>5/5</p><p>Our dataset comprises also CT and MRI scans with patients lesions segmented by an expert.<br>This allowed us to look at the distribution of lesions cluster-wise, and validate the associations between symptoms and lesions.</p><p>Check our pre-print and comment, make questions, offer suggestions!<br>Although it is not simple to share data, we will release code soon, as a means to replicate the approach on similar data and more.<br>The link is already in the paper!<br>And let us know if you have data you'd like to share and analyse with our developing methods👨🏾‍💻</p><p>We are deciding on the best match for a journal to review and possibly publish this work, of which I am super proud and thankful to co-authors Andrea Zanola, Antonio Bisogno, Silvia Facchini, Lorenzo Pini, Manfredo Atzori, and Maurizio Corbetta!</p><p><a href="https://neuromatch.social/tags/scicomm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>scicomm</span></a> <a href="https://neuromatch.social/tags/paperthread" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paperthread</span></a> <a href="https://neuromatch.social/tags/preprints" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>preprints</span></a> <a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuroscience</span></a> <a href="https://neuromatch.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://neuromatch.social/tags/mri" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>mri</span></a> <a href="https://neuromatch.social/tags/stroke" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>stroke</span></a> <a href="https://neuromatch.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a></p>
Fabrice Tshimanga<p>4/n</p><p>Reverting our General Distance matrix into the General Similarity matrix yields an ambiguous spectrum, whose eigenvalues do not help to determine the number of clusters in the data.<br>But repeating clustering and tracing which subjects consistently get clustered together, actually yields the right information, encoded in a co-occurrence matrix.<br>This latter is quite evidently composed of 5 main clusters.<br>Our second approach, affinity propagation, found autonomously 7 clusters, that are mainly finer grained partitions of the former 5.</p><p><a href="https://neuromatch.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://neuromatch.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a></p>
Fabrice Tshimanga<p>3/n</p><p>We thus decided to use the General Distance Measure to compute pairwise similarities between our 172 subjects, and obtained a matrix, which as math savy people know, is also the description of a network (an "adjacency matrix" for a "weighted undirected graph").<br>The problem was then to find cliques, communities or clusters of similar patients in such a network, and we used spectral clustering.<br>Spectral clustering is a family of techniques that use spectra of matrices describing networks, i.e. use eigenvalues of matrices to understand the structure of those networks.</p><p><a href="https://neuromatch.social/tags/spectralanalysis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spectralanalysis</span></a> <a href="https://neuromatch.social/tags/spectralclustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spectralclustering</span></a> <a href="https://neuromatch.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuroscience</span></a></p>
Fabrice Tshimanga<p>1/n<br>Our pre-print is finally out!<br>Here's my first <a href="https://neuromatch.social/tags/paperthread" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paperthread</span></a> 🧵<br>In this work, co-authors and I clustered ischaemic stroke patients profiles, and recovered common patterns of cognitive, sensorimotor damage.</p><p>...Historically many focal lesions to specific cortical areas were associated with specific distinction, but most strokes involve subcortical regions and bring multivariate patterns of deficits.<br>To characterize those patterns, many studies have turned to correlation analysis, factor analysis, PCA, focusing on the relations among variables==domains of impairments...</p><p><a href="https://www.medrxiv.org/content/10.1101/2023.11.08.23297808" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">medrxiv.org/content/10.1101/20</span><span class="invisible">23.11.08.23297808</span></a></p><p><a href="https://neuromatch.social/tags/stroke" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>stroke</span></a> <a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuroscience</span></a> <a href="https://neuromatch.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://neuromatch.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a></p>
Sven Lieber<p>Hey <a href="https://hcommons.social/tags/library" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>library</span></a> folks 👋 ,</p><p>do you want to cluster your book editions with the well-known Work-set algorithm from <a href="https://hcommons.social/tags/OCLC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCLC</span></a>, but you don't find a suitable reusable tool?</p><p>I recently faced this issue while working on the <a href="https://hcommons.social/tags/BELTRANS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BELTRANS</span></a> project at KBR (Royal Library of Belgium). All I found were many research papers describing the clustering and a few implementations that required me to install 2010-style Java software stacks.</p><p>So I decided to write an easily reusable small <a href="https://hcommons.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> script that follows the ideas of the Work-set algorithm: clustering based on descriptive keys. Nothing more, nothing less.</p><p>Check my blog post for more information and have a look at the script.</p><p>➡️ blog post: <a href="https://doi.org/10.59350/4hd4r-1tk44" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.59350/4hd4r-1tk44</span><span class="invisible"></span></a></p><p>➡️ script: <a href="https://doi.org/10.5281/zenodo.10011416" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">doi.org/10.5281/zenodo.1001141</span><span class="invisible">6</span></a></p><p><a href="https://hcommons.social/tags/FRBRization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FRBRization</span></a> <a href="https://hcommons.social/tags/FRBR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FRBR</span></a> <a href="https://hcommons.social/tags/IFLA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IFLA</span></a> <a href="https://hcommons.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a></p>
Victoria Stuart 🇨🇦 🏳️‍⚧️<p>CommunityFish: A Poisson-based Document Scaling With Hierarchical Clustering<br><a href="https://arxiv.org/abs/2308.14873" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2308.14873</span><span class="invisible"></span></a></p><p>* document scaling a key component in text-as-data applications for social scientists<br>* major field of interest for political researchers<br>* uncover differences between speakers or parties w. the help of different probabilistic / non-probabilistic approaches</p><p><a href="https://mastodon.social/tags/WordFish" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WordFish</span></a> <a href="https://mastodon.social/tags/CommunityFish" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CommunityFish</span></a> <a href="https://mastodon.social/tags/corpora" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>corpora</span></a> <a href="https://mastodon.social/tags/DocumentScaling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DocumentScaling</span></a> <a href="https://mastodon.social/tags/NLP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLP</span></a> <a href="https://mastodon.social/tags/TopicModels" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TopicModels</span></a> <a href="https://mastodon.social/tags/semantics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>semantics</span></a> <a href="https://mastodon.social/tags/ranking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ranking</span></a> <a href="https://mastodon.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://mastodon.social/tags/LDA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LDA</span></a> <a href="https://mastodon.social/tags/politics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>politics</span></a></p>
Published papers at TMLR<p>Deep Plug-and-Play Clustering with Unknown Number of Clusters</p><p>An Xiao, Hanting Chen, Tianyu Guo, QINGHUA ZHANG, Yunhe Wang</p><p>Action editor: Bo Han.</p><p><a href="https://openreview.net/forum?id=6rbcq0qacA" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=6rbcq0</span><span class="invisible">qacA</span></a></p><p><a href="https://sigmoid.social/tags/clusters" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clusters</span></a> <a href="https://sigmoid.social/tags/clustering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>clustering</span></a> <a href="https://sigmoid.social/tags/classified" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>classified</span></a></p>