<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>Samuel Pröll - Homepage</title>
        <link>https://samproell.io/</link>
        <description>Data Science | ML | Python</description>
        <generator>Hugo -- gohugo.io</generator><language>en-us</language><managingEditor>info@samproell.at (Samuel Pröll)</managingEditor>
            <webMaster>info@samproell.at (Samuel Pröll)</webMaster><lastBuildDate>Sat, 27 Dec 2025 12:32:20 &#43;0200</lastBuildDate>
            <atom:link href="https://samproell.io/index.xml" rel="self" type="application/rss+xml" />
        <item>
    <title>Customizing a gesture recognition model with MediaPipe</title>
    <link>https://samproell.io/posts/ai/asl-detector-with-mediapipe-wsl/</link>
    <pubDate>Sun, 07 Apr 2024 10:40:20 &#43;0200</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/ai/asl-detector-with-mediapipe-wsl/</guid>
    <description><![CDATA[MediaPipe1 is an amazing library of ready-to-use deep learning models for common tasks in various domains. My previous post highlights how you can use it to easily detect facial landmarks. There are many other solutions available to explore. In this post however, I want to take a look at another feature, the MediaPipe Model Maker. Model maker allows you to extend the functionality of some MediaPipe solutions by customizing models to your specific use case.]]></description>
</item><item>
    <title>Facial landmark detection is still easy with MediaPipe (2023 update)</title>
    <link>https://samproell.io/posts/ai/mediapipe-update-2023/</link>
    <pubDate>Wed, 01 Nov 2023 14:42:33 &#43;0100</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/ai/mediapipe-update-2023/</guid>
    <description><![CDATA[In 2023, MediaPipe has seen a major overhaul and now provides various new features in addition to a more versatile API. While code from my older post still works (as of writing - November 2023, mediapipe==0.10.7), I want to briefly take a look at the new API and recreate the rotating face using it.
MediaPipe preview  Note that as of November 2023, MediaPipe is still in preview and the API could change again in coming versions.]]></description>
</item><item>
    <title>ECG R peak detection in Python: a comparison of libraries</title>
    <link>https://samproell.io/posts/signal/ecg-library-comparison/</link>
    <pubDate>Sun, 21 May 2023 08:27:29 &#43;0200</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/signal/ecg-library-comparison/</guid>
    <description><![CDATA[For decades now, electrocardiography (ECG) has been a crucial tool in medicine. And with wearable ECG devices making their way into clinical settings, the amount of ECG data available will continue to increase1. Automatic detection of heart beats (R peaks, QRS complexes) is an important step in ECG analysis. In this post, we will compare some of the libraries you may come across when looking for a ready-to-use solution in Python.]]></description>
</item><item>
    <title>Managing multi-dimensional datasets with metadata in Python</title>
    <link>https://samproell.io/posts/datascience/metadata-in-machinelearning/</link>
    <pubDate>Sun, 30 Oct 2022 10:32:07 &#43;0200</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/datascience/metadata-in-machinelearning/</guid>
    <description><![CDATA[What many datasets for machine learning tutorials are lacking is metadata. Example datasets are, with good reason, kept as simple as possible and only capture the core of the problem. In the real world however, a business goal very rarely comes as one neat pack of uniform data. You may have CT images obtained with different scanners, manufacturing data from different facilities, sales data including different marketing campaigns&hellip; When working on a particular task, you want to be aware of such information, as disregarding it may lead to unexpected model behavior.]]></description>
</item><item>
    <title>My personal COVID-19 experience: a data project</title>
    <link>https://samproell.io/posts/datascience/covid-experience/</link>
    <pubDate>Fri, 12 Aug 2022 19:35:05 &#43;0200</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/datascience/covid-experience/</guid>
    <description><![CDATA[Covid knocked me out quite good. I contracted the virus right at the start of summer and spent more than a week in bed &ndash; with aching limbs, a sore throat and body temperature almost reaching 40°C. Immediately after the first positive antigen test I decided to monitor my body more closely and generate some data to play with later.
This post summarizes what I have learned through making a data project out of my Covid infection.]]></description>
</item><item>
    <title>Speed up data exploration with ad-hoc data filters in Streamlit</title>
    <link>https://samproell.io/posts/datascience/adhoc-data-filters-streamlit/</link>
    <pubDate>Thu, 30 Jun 2022 02:57:26 &#43;0200</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/datascience/adhoc-data-filters-streamlit/</guid>
    <description><![CDATA[I love Streamlit. It is an amazing tool, to quickly create interactive data apps. In data science, it is often beneficial to get first results early and then improve iteratively. Making data available and accessible to domain experts is an important step in that journey.
With Streamlit, it is straightforward to build custom applications. Apps can easily be tailored to specific data science projects. But with a few tricks, they can also be made more generally applicable.]]></description>
</item><item>
    <title>Finding peaks in noisy signals (with Python and JavaScript)</title>
    <link>https://samproell.io/posts/signal/peak-finding-python-js/</link>
    <pubDate>Thu, 26 May 2022 18:41:07 &#43;0200</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/signal/peak-finding-python-js/</guid>
    <description><![CDATA[Looking to find peaks in ECG?  There is no need to reinvent the wheel. A number of great libraries may provide what you need. Check out my comparison of ECG peak detection libraries in Python.   In many signal processing applications, finding peaks is an important part of the pipeline. Peak detection can be a very challenging endeavor, even more so when there is a lot of noise. In this post, I am investigating different ways to find peaks in noisy signals.]]></description>
</item><item>
    <title>Digital filters for live signal processing in Python</title>
    <link>https://samproell.io/posts/yarppg/yarppg-live-digital-filter/</link>
    <pubDate>Fri, 08 Apr 2022 16:35:05 &#43;0100</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/yarppg/yarppg-live-digital-filter/</guid>
    <description><![CDATA[Digital filters are commonplace in biosignal processing. And the SciPy library offers a strong digital signal processing (DSP) ecosystem that is exceptionally well documented and easy to use with offline data. However, there is shockingly little material online on DSP in Python for real-time applications. In a live graphical interface (like yarppg), the signal needs to be processed while it is being generated - one sample at a time.
In this post, I am showing two different implementations of digital filters, that can be used in a real-time setting.]]></description>
</item><item>
    <title>Applying digital filters in Python</title>
    <link>https://samproell.io/posts/yarppg/digital-filters-python/</link>
    <pubDate>Wed, 06 Apr 2022 18:55:32 &#43;0200</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/yarppg/digital-filters-python/</guid>
    <description><![CDATA[Digital filters are an important tool in signal processing. The SciPy library provides functionality to design and apply different kinds of filters. It is designed for offline use and thus, however, not really suited for real-time applications. In the next post, I am highlighting how live versions of the SciPy filters are implemented in yarppg, a video-based heart rate measurement system. Before looking into the implementations, let&rsquo;s discuss what digital filters can do and why they are so important in signal processing.]]></description>
</item><item>
    <title>Extracting heartbeat signals from webcam video</title>
    <link>https://samproell.io/posts/yarppg/yarppg-extract-heartbeat-signals/</link>
    <pubDate>Fri, 18 Mar 2022 10:42:03 &#43;0100</pubDate>
    <author>Samuel Pröll</author>
    <guid>https://samproell.io/posts/yarppg/yarppg-extract-heartbeat-signals/</guid>
    <description><![CDATA[MediaPipe update 2023  Please note that MediaPipe has seen major changes in 2023 and now offers a redesigned API. The code in this posts still works as of mediapipe==0.10.7. Check out this post for more details on the new API.   With every heartbeat, the color of your skin changes slightly. While this effect is invisible to the human eye, a normal camera is able to pick up these tiny differences.]]></description>
</item></channel>
</rss>
