{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:34:18Z","timestamp":1779100458677,"version":"3.51.4"},"reference-count":34,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T00:00:00Z","timestamp":1744848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002946","name":"German Federal Ministry of Economic Affairs and Climate Action","doi-asserted-by":"publisher","award":["50WK2270B"],"award-info":[{"award-number":["50WK2270B"]}],"id":[{"id":"10.13039\/501100002946","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Particle tracking velocimetry (PTV) forms the basis for many fluid dynamic experiments, in which individual particles are tracked across multiple successive images. However, when the experimental setup involves high-speed, high-density particles that are indistinguishable and follow complex or unknown flow fields, matching particles between images becomes significantly more challenging. Reliable PTV algorithms are crucial in such scenarios. Previous work has demonstrated that the Self-Organizing Map (SOM) machine learning approach offers superior outcomes on complex-plasma data compared with traditional methods, though its performance is sensitive to hyperparameter calibration, which requires optimization for specific flow scenarios. In this article, we describe how the dependence of the various hyperparameters on different flow scenarios was studied and the optimal settings for diverse flow conditions were identified. Based on these results, automatic hyperparameter calibration was implemented in the PTV framework. Furthermore, the SOM\u2019s performance was directly compared with that of the preceding conventional PTV method, Trackpy, for complex plasmas using synthetic data. Finally, as a new approach to identifying incorrectly matched particle traces, a Long Short-Term Memory (LSTM) neural network was developed to sort out all inaccuracies to further improve the outcome. Combined with automatic hyperparameter calibration, outlier detection and additional computational speed optimization, this work delivers a robust, versatile and efficient framework for PTV analysis.<\/jats:p>","DOI":"10.3390\/make7020037","type":"journal-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T20:05:56Z","timestamp":1744920356000},"page":"37","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Advancing Particle Tracking: Self-Organizing Map Hyperparameter Study and Long Short-Term Memory-Based Outlier Detection"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9596-7671","authenticated-orcid":false,"given":"Max","family":"Klein","sequence":"first","affiliation":[{"name":"NanoP, THM University of Applied Sciences, 35390 Giessen, Germany"},{"name":"I. Institute of Physics, Justus Liebig University, 35392 Giessen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9158-4034","authenticated-orcid":false,"given":"Niklas","family":"Dormagen","sequence":"additional","affiliation":[{"name":"NanoP, THM University of Applied Sciences, 35390 Giessen, Germany"},{"name":"I. Institute of Physics, Justus Liebig University, 35392 Giessen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8970-8203","authenticated-orcid":false,"given":"Lukas","family":"Wimmer","sequence":"additional","affiliation":[{"name":"I. Institute of Physics, Justus Liebig University, 35392 Giessen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus H.","family":"Thoma","sequence":"additional","affiliation":[{"name":"I. Institute of Physics, Justus Liebig University, 35392 Giessen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike","family":"Schwarz","sequence":"additional","affiliation":[{"name":"NanoP, THM University of Applied Sciences, 35390 Giessen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Dabiri, D., and Pecora, C. (2019). Particle tracking techniques. Particle Tracking Velocimetry, IOP Publishing.","DOI":"10.1088\/978-0-7503-2203-4"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"033001","DOI":"10.1088\/1367-2630\/adb876","article-title":"Impact of particle charge and electrorheology-effects on dust-acoustic waves in low pressure complex plasma under microgravity","volume":"27","author":"Wimmer","year":"2025","journal-title":"New J. Phys."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/TPS.2017.2744682","article-title":"Turbulence in an auto-oscillating complex plasma","volume":"46","author":"Schwabe","year":"2017","journal-title":"IEEE Trans. Plasma Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/s12217-023-10038-z","article-title":"Dust cloud convections in inhomogeneously heated plasmas in microgravity","volume":"35","author":"Schmitz","year":"2023","journal-title":"Microgravity Sci. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1038\/379806a0","article-title":"Melting dynamics of a plasma crystal","volume":"379","author":"Thomas","year":"1996","journal-title":"Nature"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"093505","DOI":"10.1063\/1.4962696","article-title":"Plasmakristall-4: New complex (dusty) plasma laboratory on board the International Space Station","volume":"87","author":"Pustylnik","year":"2016","journal-title":"Rev. Sci. Instrum."},{"key":"ref_7","unstructured":"Allan, D.B., Caswell, T., Keim, N.C., van der Wel, C.M., and Verweij, R.W. (2023). Soft-Matter\/Trackpy, v0.6.1, Zenodo."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Klein, M., Dormagen, N., Schmitz, A.S., Thoma, M.H., and Schwarz, M. (2023, January 15\u201317). Machine Learning Approach for Particle Matching, Tracing and Velocimetry with Self-Organizing Map: Application to Complex Plasmas. Proceedings of the 2023 International Conference on Machine Learning and Applications (ICMLA), Jacksonville, FL, USA.","DOI":"10.1109\/ICMLA58977.2023.00123"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/BF00226565","article-title":"Full-field bubbly flow velocity measurements using a multiframe particle tracking technique","volume":"12","author":"Hassan","year":"1991","journal-title":"Exp. Fluids"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00223406","article-title":"Particle tracking velocimetry in three-dimensional flows: Part II: Particle tracking","volume":"15","author":"Malik","year":"1993","journal-title":"Exp. Fluids"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/s00348-005-0068-7","article-title":"A quantitative study of three-dimensional Lagrangian particle tracking algorithms","volume":"40","author":"Ouellette","year":"2006","journal-title":"Exp. Fluids"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1299\/jsmeb.36.279","article-title":"Three-Dimensional PTV Based on Binary Cross-Correlation Method: Algorithm of Particle Identification","volume":"36","author":"Yamamoto","year":"1993","journal-title":"JSME Int. J. Ser. Fluids Therm. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1088\/0957-0233\/3\/7\/001","article-title":"PIV flow visualisation using particle tracking techniques","volume":"3","author":"Hassan","year":"1992","journal-title":"Meas. Sci. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/BF03182453","article-title":"Development and evaluation of an improved correlation based PTV method","volume":"4","author":"Saga","year":"2001","journal-title":"J. Vis."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1088\/0957-0233\/6\/5\/012","article-title":"An improved cross correlation technique for particle image velocimetry","volume":"6","author":"Jambunathan","year":"1995","journal-title":"Meas. Sci. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/36.368206","article-title":"A relaxation labeling technique for computing sea surface velocities from sea surface temperature","volume":"33","author":"Wu","year":"1995","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/BF01893303","article-title":"A new two-frame particle tracking algorithm using match probability","volume":"22","author":"Baek","year":"1996","journal-title":"Exp. Fluids"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1088\/0957-0233\/11\/6\/303","article-title":"Particle-tracking velocimetry with new algorithms","volume":"11","author":"Ohmi","year":"2000","journal-title":"Meas. Sci. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s00348-010-0907-z","article-title":"Integrating cross-correlation and relaxation algorithms for particle tracking velocimetry","volume":"50","author":"Brevis","year":"2011","journal-title":"Exp. Fluids"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/BF00189704","article-title":"An investigation of the performance of multi layer, neural networks applied to the analysis of PIV images","volume":"19","author":"Grant","year":"1995","journal-title":"Exp. Fluids"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1007\/s003480050297","article-title":"A new neural network for particle-tracking velocimetry","volume":"26","year":"1999","journal-title":"Exp. Fluids"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"890","DOI":"10.1016\/j.amc.2008.05.101","article-title":"SOM-based particle matching algorithm for 3D particle tracking velocimetry","volume":"205","author":"Ohmi","year":"2008","journal-title":"Appl. Math. Comput."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ji, L., Yang, F., and Guan, M. (2015, January 24\u201326). The Application of SOM Network to Particle Tracking Velocimetry in a Wind-Blown Sand Flow. Proceedings of the 2015 2nd International Conference on Information Science and Control Engineering, Shanghai, China.","DOI":"10.1109\/ICISCE.2015.114"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1007\/s00348-014-1705-9","article-title":"Rod-like particles matching algorithm based on SOM neural network in dispersed two-phase flow measurements","volume":"55","author":"Zavareh","year":"2014","journal-title":"Exp. Fluids"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1088\/0957-0233\/11\/6\/311","article-title":"Standard images for particle-image velocimetry","volume":"11","author":"Okamoto","year":"2000","journal-title":"Meas. Sci. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/BF00191015","article-title":"Measurement of the flow field in a diesel engine combustion chamber after combustion by cross-correlation of high-speed photographs","volume":"20","author":"Sun","year":"1996","journal-title":"Exp. Fluids"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/s003480050300","article-title":"A new tracking algorithm of PIV and removal of spurious vectors using Delaunay tessellation","volume":"26","author":"Song","year":"1999","journal-title":"Exp. Fluids"},{"key":"ref_28","first-page":"4927","article-title":"Error detection and performance analysis scheme for particle tracking velocimetry results using fuzzy logic","volume":"5","author":"Sapkota","year":"2009","journal-title":"Int. J. Innov. Comput. Inf. Control"},{"key":"ref_29","unstructured":"Chen, Z., Lu, W., Bhong, R., Hu, Y., Freeman, B., and Carpenter, A. (2024). Anomaly Detection of Particle Orbit in Accelerator using LSTM Deep Learning Technology. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3127","DOI":"10.1109\/TNNLS.2019.2935975","article-title":"Unsupervised anomaly detection with LSTM neural networks","volume":"31","author":"Ergen","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_31","unstructured":"Saha, S., Sarkar, J., Dhavala, S., Sarkar, S., and Mota, P. (2023). Quantile LSTM: A Robust LSTM for Anomaly Detection In Time Series Data. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1186\/s40537-023-00746-z","article-title":"Unsupervised outlier detection for time-series data of indoor air quality using LSTM autoencoder with ensemble method","volume":"10","author":"Park","year":"2023","journal-title":"J. Big Data"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hug, R., Becker, S., H\u00fcbner, W., and Arens, M. (2018, January 18\u201321). Particle-based pedestrian path prediction using LSTM-MDL models. Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Gold Coast, QLD, Australia.","DOI":"10.1109\/ITSC.2018.8569478"},{"key":"ref_34","unstructured":"Kingma, D.P. (2014). Adam: A method for stochastic optimization. arXiv."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/2\/37\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:16:42Z","timestamp":1760030202000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/2\/37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,17]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["make7020037"],"URL":"https:\/\/doi.org\/10.3390\/make7020037","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,17]]}}}