TU Wien Research Data
Not a member yet
512 research outputs found
Sort by
Cascade of magnetic-field-driven quantum phase transitions in Ce3Pd20Si6: Figures data
No full text<p>The text files contain the data that has been used to create the figures in the publication "Cascade of magnetic-field-driven quantum phase transitions in Ce3Pd20Si6"</p>
<p>The data are tab separated and can be used without any specific script. Explanations of the content are as follow:</p>
<p><strong>Fig3:</strong> Field-induced magnetic Bragg intensity at Q = (111), measured at T = 50 mK as a function of the magnetic field applied along the [112] direction.</p>
<p><strong>Fig4:</strong><br>(a) and (b): A selection of unprocessed INS data taken at T = 0.05 K at Q = (111) and (110), respectively, in magnetic fields of 7, 9.5, 12, and 13.5 T applied along [112], presented as offset plot. Files (a_1) and (b_1) are the fits of the respective measured curves<br> (c): Data collected at the highet magnetic field of 14.5 T at different Q vectors. File (c_1) contains the fits of the respective curves.<br>(d) and (e): Magnetic field dependence of the inelastic peak positions extracted from the fits from the curves measured at Q = (111) and Q = (-110).</p>
<p><strong>Fig5: </strong>Dispersion of field-induced magnetic excitations in Ce3Pd20Si6 measured in a magnetic field of 14.5 T applied along the [112] axis. The color map is composed of energy scans such as those in Fig. 4(c), measured along high-symmetry directions following the polygonal path (0.4 0.4 0.4)–(111)–(110)–(-0.5 0.5 0). The fitted peak position are shown as data points Fig5_1; the lines are an empirical fit to the data (Fig5_1).</p>
<p>Important Note on Fig.5: Fig5 is a 15x50 matrix with the color coded intensities. (NaN = Not a Number means the point was not measured to save time). Here the data presented can be reproduced as follows:</p>
<ul>
<li>Y-spacing is 0.05meV (range is from 0 to 2.5meV), </li>
<li>X-spacing is (2*pi/a)*sqrt(h^2 + k^2 + l^2) and</li>
<li>range is (0.4,0.4,0.4)-(1,1,1)-(-1,1,0)-(-0.5,0.5,0). </li>
</ul>
<p>where h,k,l are the Miller indices.</p>
<p>Fig5_1 contains the fitted peak positions and dispersion as well as the X and Y-spacings (r.l.u. and energy respectively).</p>
Data - Werginz et al. - Differential intrinsic firing properties in sustained and transient mouse αRGCs match their light response characteristics and persist during retinal degeneration
No full text<h2>Patch clamp data associated with <em>Werginz et al. - Differential intrinsic firing properties in sustained and transient mouse αRGCs match their light response characteristics and persist during retinal degeneration</em></h2>
<p>Data, as well as simplified load and plot functions. The data is the basis for figures 1, 2, 3 and 5 in Werginz et al. (<a href="https://doi.org/10.1523/JNEUROSCI.1592-24.2024">10.1523/JNEUROSCI.1592-24.2024</a>). Functionality includes loading results from a specified retinal ganglion cell (RGC) and plotting spiking output (e.g., membrane voltage over time) in response to visual stimulation as well as long (500 ms) and short (3 ms) current injections into the soma. Provided code does not perform threshold searching or other, more complex, analysis.</p>
<h3>Context and methodology</h3>
<ul>
<li>Data was created by patch clamp electrophysiology of mouse alpha retinal ganglion cells (RGCs)</li>
<li>Light as well as intracellular stimulation was applied to test intinsic properties of different types of RGCs.</li>
</ul>
<h3>Technical details</h3>
<ul>
<li>Data can directly be loaded and plotted in Matlab running <em>plotData.m</em> (tested in Matlab R2024b)</li>
<li>Parameters to be specified:
<ul>
<li><em>cellID</em> - identifier of each recorded cell, see list on top of <em>plotData.m</em>. Don't forget to add the folder prefix specifiying cell type (<em>ONS</em>, <em>OFFS</em> or <em>OFFT</em>)</li>
</ul>
</li>
<li>The <em>Data</em> folder is structured into different cell types (<em>ONS</em>, <em>OFFS</em> or <em>OFFT</em>) data</li>
<li>The <em>helperFunctions</em> folder includes additional methods to extract and plot data</li>
<li>If help is needed feel free to reach out to Paul Werginz</li>
</ul>
<p>Data is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0), the scripts are licensed under a MIT License.</p><p>Retinal ganglion cells (RGCs) are the neuronal connections between the eye and the brain conveying multiple features of the outside world through parallel pathways. While there is a large body of literature on how these pathways arise in the retinal network, the process of converting presynaptic inputs into RGC spiking output is little understood. In this study, we show substantial differences in the spike generator across three types of αRGCs in female and male mice, the αON sustained, αOFF sustained, and αOFF transient RGC. The differences in their intrinsic spiking responses match the differences in the light responses across RGC types. While sustained RGC types have spike generators that are able to generate sustained trains of action potentials at high rates, the transient RGC type fired shortest action potentials enabling it to fire high-frequency transient bursts. The observed differences were also present in late-stage photoreceptor-degenerated retina demonstrating long-term functional stability of RGC responses even when presynaptic circuitry is deteriorated for long periods of time. Our results demonstrate that intrinsic cell properties support the presynaptic retinal computation and are, once established, independent of them.</p>
Woll kumbt der may (Jud_1523-2_n13) Audio recording
No full text<h1>Audio recording of a lute piece from the E-LAUTE project</h1><h2>Overview</h2><p>This dataset contains an audio recording of the piece "Woll kumbt der may", a 16th century lute music piece originally notated in lute tablature, created as part of the E-LAUTE project (<a href="https://e-laute.info/">https://e-laute.info/</a>). The recording preserves and makes historical lute music from the German-speaking regions during 1450-1550 accessible.</p><p>The recording is based on the work with the title "Woll kumbt der may" and the id "Jud_1523-2_n13" in the e-lautedb. It is found on the page(s) or folio(s) 19r-19v in the source "1.5.2.3. Ain schone kunstliche vnderweisung" with the source-id "Jud_1523-2".</p><p>The original source and multiple transcriptions of the work can be found on the E-LAUTE platform: <a href="https://edition.onb.ac.at/fedora/objects/o:lau.Jud_1523-2/methods/sdef:TEI/get?mode=n13" target="_blank">https://edition.onb.ac.at/fedora/objects/o:lau.Jud_1523-2/methods/sdef:TEI/get?mode=n13</a>.</p><p>Links to the source: <a href="http://data.onb.ac.at/rec/AC09185338" target="_blank">http://data.onb.ac.at/rec/AC09185338</a>, <a href="https://opac.rism.info/rism/Record/rism990032736" target="_blank">https://opac.rism.info/rism/Record/rism990032736</a>, <a href="https://gateway-bayern.de/VD16+J+1031" target="_blank">https://gateway-bayern.de/VD16+J+1031</a>, .</p><h2>Dataset Contents</h2><p>This dataset includes:</p><ul><li><strong>Audio file</strong>: An audio recording of the lute piece in .wav format</li> <li><strong>Metadata file</strong>: A metadata file with detailed information about the recording in .json format</li></ul><h2>About the E-LAUTE Project</h2><p><strong>E-LAUTE: Electronic Linked Annotated Unified Tablature Edition - The Lute in the German-Speaking Area 1450-1550</strong></p><p>The E-LAUTE project creates innovative digital editions of lute tablatures from the German-speaking area between 1450 and 1550. This interdisciplinary "open knowledge platform" combines musicology, music practice, music informatics, and literary studies to transform traditional editions into collaborative research spaces.</p><p>For more information, visit the project website: <a href="https://e-laute.info/">https://e-laute.info/</a></p>
Tripl (A-Wn_Mus.Hs._18688_n48) Audio recording
No full text<h1>Audio recording of a lute piece from the E-LAUTE project</h1><h2>Overview</h2><p>This dataset contains an audio recording of the piece "Tripl", a 16th century lute music piece originally notated in lute tablature, created as part of the E-LAUTE project (<a href="https://e-laute.info/">https://e-laute.info/</a>). The recording preserves and makes historical lute music from the German-speaking regions during 1450-1550 accessible.</p><p>The recording is based on the work with the title "Tripl" and the id "A-Wn_Mus.Hs._18688_n48" in the e-lautedb. It is found on the page(s) or folio(s) 28r in the source "[Lautentabulatur des Stephan Craus]" with the source-id "A-Wn_Mus.Hs._18688".</p><p>The original source and multiple transcriptions of the work can be found on the E-LAUTE platform: <a href="https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n48" target="_blank">https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n48</a>.</p><p>Links to the source: <a href="http://data.onb.ac.at/rec/AC14316391" target="_blank">http://data.onb.ac.at/rec/AC14316391</a>, <a href="https://rism.online/sources/600141880" target="_blank">https://rism.online/sources/600141880</a>, .</p><h2>Dataset Contents</h2><p>This dataset includes:</p><ul><li><strong>Audio file</strong>: An audio recording of the lute piece in .wav format</li> <li><strong>Metadata file</strong>: A metadata file with detailed information about the recording in .json format</li></ul><h2>About the E-LAUTE Project</h2><p><strong>E-LAUTE: Electronic Linked Annotated Unified Tablature Edition - The Lute in the German-Speaking Area 1450-1550</strong></p><p>The E-LAUTE project creates innovative digital editions of lute tablatures from the German-speaking area between 1450 and 1550. This interdisciplinary "open knowledge platform" combines musicology, music practice, music informatics, and literary studies to transform traditional editions into collaborative research spaces.</p><p>For more information, visit the project website: <a href="https://e-laute.info/">https://e-laute.info/</a></p>
[Preambulum] (A-Wn_Mus.Hs._18688_n11) Audio recording
No full text<h1>Audio recording of a lute piece from the E-LAUTE project</h1><h2>Overview</h2><p>This dataset contains an audio recording of the piece "[Preambulum]", a 16th century lute music piece originally notated in lute tablature, created as part of the E-LAUTE project (<a href="https://e-laute.info/">https://e-laute.info/</a>). The recording preserves and makes historical lute music from the German-speaking regions during 1450-1550 accessible.</p><p>The recording is based on the work with the title "[Preambulum]" and the id "A-Wn_Mus.Hs._18688_n11" in the e-lautedb. It is found on the page(s) or folio(s) 9r_4-8 in the source "[Lautentabulatur des Stephan Craus]" with the source-id "A-Wn_Mus.Hs._18688".</p><p>The original source and multiple transcriptions of the work can be found on the E-LAUTE platform: <a href="https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n11" target="_blank">https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n11</a>.</p><p>Links to the source: <a href="http://data.onb.ac.at/rec/AC14316391" target="_blank">http://data.onb.ac.at/rec/AC14316391</a>, <a href="https://rism.online/sources/600141880" target="_blank">https://rism.online/sources/600141880</a>, .</p><h2>Dataset Contents</h2><p>This dataset includes:</p><ul><li><strong>Audio file</strong>: An audio recording of the lute piece in .wav format</li> <li><strong>Metadata file</strong>: A metadata file with detailed information about the recording in .json format</li></ul><h2>About the E-LAUTE Project</h2><p><strong>E-LAUTE: Electronic Linked Annotated Unified Tablature Edition - The Lute in the German-Speaking Area 1450-1550</strong></p><p>The E-LAUTE project creates innovative digital editions of lute tablatures from the German-speaking area between 1450 and 1550. This interdisciplinary "open knowledge platform" combines musicology, music practice, music informatics, and literary studies to transform traditional editions into collaborative research spaces.</p><p>For more information, visit the project website: <a href="https://e-laute.info/">https://e-laute.info/</a></p>
[Ungleicher prunst lieb und huld] (A-Wn_Mus.Hs._18688_n52) Audio recording
No full text<h1>Audio recording of a lute piece from the E-LAUTE project</h1><h2>Overview</h2><p>This dataset contains an audio recording of the piece "[Ungleicher prunst lieb und huld]", a 16th century lute music piece originally notated in lute tablature, created as part of the E-LAUTE project (<a href="https://e-laute.info/">https://e-laute.info/</a>). The recording preserves and makes historical lute music from the German-speaking regions during 1450-1550 accessible.</p><p>The recording is based on the work with the title "[Ungleicher prunst lieb und huld]" and the id "A-Wn_Mus.Hs._18688_n52" in the e-lautedb. It is found on the page(s) or folio(s) 29v in the source "[Lautentabulatur des Stephan Craus]" with the source-id "A-Wn_Mus.Hs._18688".</p><p>The original source and multiple transcriptions of the work can be found on the E-LAUTE platform: <a href="https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n52" target="_blank">https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n52</a>.</p><p>Links to the source: <a href="http://data.onb.ac.at/rec/AC14316391" target="_blank">http://data.onb.ac.at/rec/AC14316391</a>, <a href="https://rism.online/sources/600141880" target="_blank">https://rism.online/sources/600141880</a>, .</p><h2>Dataset Contents</h2><p>This dataset includes:</p><ul><li><strong>Audio file</strong>: An audio recording of the lute piece in .wav format</li> <li><strong>Metadata file</strong>: A metadata file with detailed information about the recording in .json format</li></ul><h2>About the E-LAUTE Project</h2><p><strong>E-LAUTE: Electronic Linked Annotated Unified Tablature Edition - The Lute in the German-Speaking Area 1450-1550</strong></p><p>The E-LAUTE project creates innovative digital editions of lute tablatures from the German-speaking area between 1450 and 1550. This interdisciplinary "open knowledge platform" combines musicology, music practice, music informatics, and literary studies to transform traditional editions into collaborative research spaces.</p><p>For more information, visit the project website: <a href="https://e-laute.info/">https://e-laute.info/</a></p>
[Paduane] (A-Wn_Mus.Hs._18688_n08) Audio recording
No full text<h1>Audio recording of a lute piece from the E-LAUTE project</h1><h2>Overview</h2><p>This dataset contains an audio recording of the piece "[Paduane]", a 16th century lute music piece originally notated in lute tablature, created as part of the E-LAUTE project (<a href="https://e-laute.info/">https://e-laute.info/</a>). The recording preserves and makes historical lute music from the German-speaking regions during 1450-1550 accessible.</p><p>The recording is based on the work with the title "[Paduane]" and the id "A-Wn_Mus.Hs._18688_n08" in the e-lautedb. It is found on the page(s) or folio(s) 8v_1-5 in the source "[Lautentabulatur des Stephan Craus]" with the source-id "A-Wn_Mus.Hs._18688".</p><p>The original source and multiple transcriptions of the work can be found on the E-LAUTE platform: <a href="https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n08" target="_blank">https://edition.onb.ac.at/fedora/objects/o:lau.A-Wn_Mus.Hs._18688/methods/sdef:TEI/get?mode=n08</a>.</p><p>Links to the source: <a href="http://data.onb.ac.at/rec/AC14316391" target="_blank">http://data.onb.ac.at/rec/AC14316391</a>, <a href="https://rism.online/sources/600141880" target="_blank">https://rism.online/sources/600141880</a>, .</p><h2>Dataset Contents</h2><p>This dataset includes:</p><ul><li><strong>Audio file</strong>: An audio recording of the lute piece in .wav format</li> <li><strong>Metadata file</strong>: A metadata file with detailed information about the recording in .json format</li></ul><h2>About the E-LAUTE Project</h2><p><strong>E-LAUTE: Electronic Linked Annotated Unified Tablature Edition - The Lute in the German-Speaking Area 1450-1550</strong></p><p>The E-LAUTE project creates innovative digital editions of lute tablatures from the German-speaking area between 1450 and 1550. This interdisciplinary "open knowledge platform" combines musicology, music practice, music informatics, and literary studies to transform traditional editions into collaborative research spaces.</p><p>For more information, visit the project website: <a href="https://e-laute.info/">https://e-laute.info/</a></p>
Das ander Priamell (Jud_1523-2_n28) Audio recording
No full text<h1>Audio recording of a lute piece from the E-LAUTE project</h1><h2>Overview</h2><p>This dataset contains an audio recording of the piece "Das ander Priamell", a 16th century lute music piece originally notated in lute tablature, created as part of the E-LAUTE project (<a href="https://e-laute.info/">https://e-laute.info/</a>). The recording preserves and makes historical lute music from the German-speaking regions during 1450-1550 accessible.</p><p>The recording is based on the work with the title "Das ander Priamell" and the id "Jud_1523-2_n28" in the e-lautedb. It is found on the page(s) or folio(s) 26r-26v in the source "1.5.2.3. Ain schone kunstliche vnderweisung" with the source-id "Jud_1523-2".</p><p>The original source and multiple transcriptions of the work can be found on the E-LAUTE platform: <a href="https://edition.onb.ac.at/fedora/objects/o:lau.Jud_1523-2/methods/sdef:TEI/get?mode=n28" target="_blank">https://edition.onb.ac.at/fedora/objects/o:lau.Jud_1523-2/methods/sdef:TEI/get?mode=n28</a>.</p><p>Links to the source: <a href="http://data.onb.ac.at/rec/AC09185338" target="_blank">http://data.onb.ac.at/rec/AC09185338</a>, <a href="https://opac.rism.info/rism/Record/rism990032736" target="_blank">https://opac.rism.info/rism/Record/rism990032736</a>, <a href="https://gateway-bayern.de/VD16+J+1031" target="_blank">https://gateway-bayern.de/VD16+J+1031</a>, .</p><h2>Dataset Contents</h2><p>This dataset includes:</p><ul><li><strong>Audio file</strong>: An audio recording of the lute piece in .wav format</li> <li><strong>Metadata file</strong>: A metadata file with detailed information about the recording in .json format</li></ul><h2>About the E-LAUTE Project</h2><p><strong>E-LAUTE: Electronic Linked Annotated Unified Tablature Edition - The Lute in the German-Speaking Area 1450-1550</strong></p><p>The E-LAUTE project creates innovative digital editions of lute tablatures from the German-speaking area between 1450 and 1550. This interdisciplinary "open knowledge platform" combines musicology, music practice, music informatics, and literary studies to transform traditional editions into collaborative research spaces.</p><p>For more information, visit the project website: <a href="https://e-laute.info/">https://e-laute.info/</a></p>
Data for binary classification experiments
No full text<h2>Research context</h2>
<p>This zip archive contains all the data and scripts which are neccessary to reproduce the results of the following paper, co-authored by Markus Kattenbeck, Ioannis Giannopoulos, Negar Alinaghi, Antonia Golab, and Daniel R. Montello:</p>
<p><strong>Predicting spatial familiarity by exploiting head and eye movements during pedestrian navigation in the real world</strong></p>
<p>This paper will be published in Springer Nature Scientific Reports.</p>
<h2>File overview</h2>
<p>The structure of the archive is the following:</p>
<ul>
<li>Folder "01_data" contains all the data files needed and a readme file describing the structure of each of these data files. These data files are:
<ul>
<li><strong>lsp.csv</strong> [contains demographic data about participants]</li>
<li><strong>matched_gaze_imu.csv</strong> [contains the segmented behavioral data, i.e. both gaze features and imu features]</li>
<li><strong>matched_gaze_imu_feature_description.pdf</strong> [contains a description of the features contained in matched_gaze_imu.csv]</li>
<li><strong>walking_dates.csv</strong> [contains an overview on which date participants walked the familiar and unfamiliar routes]</li>
<li><strong>users_polygons.csv</strong> [contains one or more polygons per participant in which they are familiar]</li>
<li><strong>polygons_markers.csv</strong> [contains locations of POIs per polygon for which participants reported to be familiar with]</li>
<li><strong>user_routes.csv</strong> [containes the route participants provided between a randomly selected pair of POIs they have provided for a given polygon]</li>
</ul>
</li>
<li>Folder "02_scripts" contains the data analysis scripts; they are organized in two subfolders:
<ul>
<li><strong>01_ml_scripts:</strong> these are the scripts for the XGBoost classification; they are organized as two python files in which further instructions for use are given.
<ul>
<li><strong>80_20_code.py</strong> is the python file which runs the ML experiments using an 80/20 train/test split</li>
<li><strong>L5O4T_code.py</strong> is the python file which runs the ML experiments leaving the full data of five different participants per condition as unseen data for the test.</li>
<li><strong>requirements.txt</strong> states the used Python package versions</li>
</ul>
</li>
<li><strong>02_r_scripts:</strong>
<ul>
<li><strong>cleaned_script.Rmd</strong> This is an R notebook which can be easily opened in R-Studio and provides the analysis scripts for the descriptive statistics presented in the paper. </li>
<li><strong>package_versions.txt</strong> states the used R package versions</li>
</ul>
</li>
</ul>
</li>
</ul>
<h2>Licenses</h2>
<p>The code is licensed under MIT, the data is licensed under CC-BY.</p>
Decoding Wayfinding: Analyzing Wayfinding Processes in the Outdoor Environment
No full text<h3>How To Cite?</h3>
<p>Alinaghi, N., Giannopoulos, I., Kattenbeck, M., & Raubal, M. (2025). Decoding wayfinding: analyzing wayfinding processes in the outdoor environment. <em>International Journal of Geographical Information Science</em>, 1–31. https://doi.org/10.1080/13658816.2025.2473599</p>
<p>Link to the paper: https://www.tandfonline.com/doi/full/10.1080/13658816.2025.2473599</p>
<h3> </h3>
<h3>Folder Structure</h3>
<p>The folder named <strong>“submission”</strong> contains the following:</p>
<ol>
<li><strong>“pythonProject”</strong>: This folder contains all the Python files and subfolders needed for analysis.</li>
<li><strong><code>ijgis.yml</code></strong>: This file lists all the Python libraries and dependencies required to run the code.</li>
</ol>
<h3>Setting Up the Environment</h3>
<ol>
<li>Use the <code>ijgis.yml</code> file to create a Python project and environment. Ensure you activate the environment before running the code.</li>
<li>The <code>pythonProject</code> folder contains several <code>.py</code> files and subfolders, each with specific functionality as described below.</li>
</ol>
<h3>Subfolders</h3>
<h4>1. <strong>Data_4_IJGIS</strong></h4>
<ul>
<li>This folder contains the data used for the results reported in the paper.</li>
<li><strong>Note</strong>: The data analysis that we explain in this paper already begins with the synchronization and cleaning of the recorded raw data. The published data is already synchronized and cleaned. Both the cleaned files and the merged files with features extracted for them are given in this directory. If you want to perform the segmentation and feature extraction yourself, you should run the respective Python files yourself. If not, you can use the “merged_…csv” files as input for the training.</li>
</ul>
<h4>2. <strong>results_[DateTime] (e.g., results_20240906_15_00_13)</strong></h4>
<ul>
<li>This folder will be generated when you run the code and will store the output of each step.</li>
<li>The current folder contains results created during code debugging for the submission.</li>
<li>When you run the code, a new folder with fresh results will be generated.</li>
</ul>
<h3>Python Files</h3>
<h4>1. <strong>helper_functions.py</strong></h4>
<ul>
<li>Contains reusable functions used throughout the analysis.</li>
<li>Each function includes a description of its purpose and the input parameters required.</li>
</ul>
<h4>2. <strong>create_sanity_plots.py</strong></h4>
<ul>
<li>Generates scatter plots like those in <strong>Figure 3</strong> of the paper.</li>
<li>Although the code has been run for all 309 trials, it can be used to check the sample data provided.</li>
<li><strong>Output</strong>: A <code>.png</code> file for each column of the raw gaze and IMU recordings, color-coded with logged events.</li>
<li><strong>Usage</strong>: Run this file to create visualizations similar to Figure 3.</li>
</ul>
<h4>3. <strong>overlapping_sliding_window_loop.py</strong></h4>
<ul>
<li>Implements overlapping sliding window segmentation and generates plots like those in <strong>Figure 4</strong>.</li>
<li><strong>Output</strong>:
<ul>
<li>Two new subfolders, <strong>“Gaze”</strong> and <strong>“IMU”</strong>, will be added to the <strong>Data_4_IJGIS</strong> folder.</li>
<li>Segmented files (default: 2–10 seconds with a 1-second step size) will be saved as <code>.csv</code> files.</li>
<li>A visualization of the segments, similar to <strong>Figure 4</strong>, will be automatically generated.</li>
</ul>
</li>
</ul>
<h4>4. <strong>gaze_features.py</strong> & <strong>imu_features.py </strong><strong>(Note: there has been an update to the IDT function implementation in the gaze_features.py on 19.03.2025.) </strong></h4>
<ul>
<li>These files compute features as explained in <strong>Tables 1</strong> and <strong>2</strong> of the paper, respectively.</li>
<li>They process the segmented recordings generated by the <code>overlapping_sliding_window_loop.py</code>.</li>
<li><strong>Usage</strong>: Just to know how the features are calculated, you can run this code after the segmentation with the sliding window and run these files to calculate the features from the segmented data.</li>
</ul>
<h4>5. <strong>training_prediction.py</strong></h4>
<ul>
<li>This file contains the main machine learning analysis of the paper. This file contains all the code for the training of the model, its evaluation, and its use for the inference of the “monitoring part”. It covers the following steps:</li>
</ul>
<h5>a. <strong>Data Preparation (corresponding to Section 5.1.1 of the paper)</strong></h5>
<ul>
<li>Prepares the data according to the research question (RQ) described in the paper. Since this data was collected with several RQs in mind, we remove parts of the data that are not related to the RQ of this paper.</li>
<li>A function named <code>plot_labels_comparison(df, save_path, x_label_freq=10, figsize=(15, 5))</code> in line 116 visualizes the data preparation results. As this visualization is not used in the paper, the line is commented out, but if you want to see visually what has been changed compared to the original data, you can comment out this line.</li>
</ul>
<h5>b. <strong>Training/Validation/Test Split</strong></h5>
<ul>
<li>Splits the data for machine learning experiments (an explanation can be found in <strong>Section 5.1.1. Preparation of data for training and inference</strong> of the paper).</li>
<li>Make sure that you follow the instructions in the comments to the code exactly.</li>
<li><strong>Output</strong>: The split data is saved as <code>.csv</code> files in the results folder.</li>
</ul>
<h5>c. <strong>Machine and Deep Learning Experiments</strong></h5>
<p>This part contains three main code blocks:</p>
<p>iii. One for the XGboost code with correct hyperparameter tuning:<br>Please read the instructions for each block carefully to ensure that the code works smoothly. Regardless of which block you use, you will get the classification results (in the form of scores) for unseen data. The way we empirically test the confidence threshold of</p>
<ul>
<li><strong>MLP Network (Commented Out)</strong>: This code was used for classification with the MLP network, and the results shown in <strong>Table 3</strong> are from this code. If you wish to use this model, please comment out the following blocks accordingly.</li>
<li><strong>XGBoost without Hyperparameter Tuning</strong>: If you want to run the code but do not want to spend time on the full training with hyperparameter tuning (as was done for the paper), just uncomment this part. This will give you a simple, untuned model with which you can achieve at least some results.</li>
<li><strong>XGBoost with Hyperparameter Tuning</strong>: If you want to train the model the way we trained it for the analysis reported in the paper, use this block (the plots in <strong>Figure 7</strong> are from this block). We ran this block with different feature sets and different segmentation files and created a simple bar chart from the saved results, shown in <strong>Figure 6</strong>.</li>
</ul>
<p><strong>Note:</strong> Please read the instructions for each block carefully to ensure that the code works smoothly. Regardless of which block you use, you will get the classification results (in the form of scores) for unseen data. The way we empirically calculated the confidence threshold of the model (explained in the paper in <strong>Section 5.2. Part II: Decoding surveillance by sequence analysis</strong>) is given in this block in lines 361 to 380.</p>
<h5>d. <strong>Inference (Monitoring Part)</strong></h5>
<ul>
<li>Final inference is performed using the monitoring data. This step produces a <code>.csv</code> file containing inferred labels.</li>
<li><strong>Figure 8</strong> in the paper is generated using this part of the code.</li>
</ul>
<h4>6. <strong>sequence_analysis.py</strong></h4>
<ul>
<li>Performs analysis on the inferred data, producing <strong>Figures 9</strong> and <strong>10</strong> from the paper.</li>
<li>This file reads the inferred data from the previous step and performs sequence analysis as described in <strong>Sections 5.2.1</strong> and <strong>5.2.2</strong>.</li>
</ul>
<h3>Licenses</h3>
<p>The data is licensed under CC-BY, the code is licensed under MIT.</p>