{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T03:57:38Z","timestamp":1790567858449,"version":"4.1.0"},"reference-count":39,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Forensic Sciences"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The production of three\u2010dimensional (3D) printed firearms is concerning as these objects are unregulated and untraceable due to the lack of serial numbers. Criminals can obtain 3D models online or design their own versions using computer\u2010aided design (CAD) software. While prior research and law enforcement efforts have focused primarily on analyzing tangible printed objects, investigations analyzing digital evidence are currently limited. This study presents a proof\u2010of\u2010concept approach for classifying firearm and non\u2010firearm objects using geometric information extracted from g\u2010code files, which serve as the executable instructions for 3D printers. It uses two feature extraction methods: the direct g\u2010code method and the mesh construction method. The direct g\u2010code method extracts the features as values directly from the g\u2010code file, while the mesh construction method converts the coordinates from the g\u2010code file into a 3D mesh, then extracts the vertices and edges from each model. We use machine learning classifiers such as random forest (RF), support vector machine, decision tree, and a convolutional neural network to classify our objects into firearm and non\u2010firearm objects. We then apply a 10\u2010fold cross validation on our data to validate its accuracy. The results demonstrated that the RF model, in conjunction with the mesh construction method, achieves the highest classification accuracy of 95.80%. The mesh construction method consistently outperforms the direct g\u2010code method accuracy results, and these performance differences are confirmed as statistically significant using a paired\n                    <jats:italic>t<\/jats:italic>\n                    \u2010test.\n                  <\/jats:p>","DOI":"10.1111\/1556-4029.70355","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T05:03:25Z","timestamp":1777352605000},"page":"1621-1638","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>3D<\/scp>\n                    printed firearm identification: A comparison of machine learning models"],"prefix":"10.1111","volume":"71","author":[{"given":"Laura","family":"Garland","sequence":"first","affiliation":[{"name":"Department of Computer Science Sam Houston State University  Huntsville Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erasmus","family":"Mfodwo","sequence":"additional","affiliation":[{"name":"Department of Computer Science Sam Houston State University  Huntsville Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashar","family":"Neyaz","sequence":"additional","affiliation":[{"name":"Department of Computer Science Wentworth Institute of Technology  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cihan","family":"Varol","sequence":"additional","affiliation":[{"name":"Department of Computer Science Sam Houston State University  Huntsville Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/10439463.2020.1730835"},{"key":"e_1_2_9_3_1","unstructured":"WhitehurstL.UnitedHealthcare CEO was likely killed with a ghost gun that can be made at home.AP News[cited 2026 Mar 4]. Available from:https:\/\/apnews.com\/article\/ghost\u2010guns\u2010unitedhealthcare\u2010ceo\u20101e3b449dd9ed5fabeb2ad592fde91575"},{"key":"e_1_2_9_4_1","unstructured":"Halle synagogue attack: Germany far\u2010right gunman jailed for life.BBC News[cited 2026 Mar 4]. Available from:https:\/\/www.bbc.com\/news\/world\u2010europe\u201055395682."},{"key":"e_1_2_9_5_1","unstructured":"MendiolaJ.16\u2010year\u2010old charged for allegedly shooting man with 3D\u2010printed gun in Des Moines.The Des Moines Register[cited 2026 Mar 4]. Available from:https:\/\/www.desmoinesregister.com\/story\/news\/crime\u2010and\u2010courts\/2024\/04\/10\/16\u2010year\u2010old\u2010charged\u2010allegedly\u2010shooting\u2010man\u2010with\u20103d\u2010printed\u2010gun\u2010des\u2010moines\u2010easton\u2010boulevard\/73278287007\/."},{"key":"e_1_2_9_6_1","unstructured":"Spain dismantles workshop making 3D\u2010printed weapons.BBC News[cited 2026 Mar 4]. Available from:https:\/\/www.bbc.com\/news\/world\u2010europe\u201056798743"},{"key":"e_1_2_9_7_1","unstructured":"WilliamsD BaumanA.Police: ghost guns and 3D printers for making them found at New York City day care.CBS News[cited 2026 Mar 4]. Available from:https:\/\/www.cbsnews.com\/newyork\/news\/police\u2010ghost\u2010guns\u2010and\u20103d\u2010printers\u2010for\u2010making\u2010them\u2010found\u2010at\u2010harlem\u2010day\u2010care\/"},{"key":"e_1_2_9_8_1","unstructured":"CovilW.He made a gun using a 3D printer then he accidentally shot himself.CBS 6 News Richmond WTVR[cited 2026 Mar 4]. Available from:https:\/\/www.wtvr.com\/news\/local\u2010news\/hopewell\u20103d\u2010printer\u2010gun"},{"key":"e_1_2_9_9_1","unstructured":"TynanD.\u2018I wouldn't waste my time\u2019: firearms experts dismiss flimsy 3D\u2010printed guns.The Guardian[cited 2024 Dec 17]. Available from:https:\/\/www.theguardian.com\/us\u2010news\/2018\/jul\/31\/3d\u2010printed\u2010guns\u2010danger\u2010problems\u2010plastic."},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apmt.2024.102306"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.forsciint.2023.111736"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.forsciint.2021.111144"},{"issue":"6","key":"e_1_2_9_13_1","first-page":"31","article-title":"Printing terror: An empirical overview of the use of 3D\u2010printed firearms by right\u2010wing extremists","volume":"17","author":"Veilleux\u2010Lepage Y","year":"2024","journal-title":"CTC Sentinel"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.2289577"},{"key":"e_1_2_9_15_1","article-title":"3\u2010D printed firearms: How we got here, the ever\u2010changing threat, and how we might prepare for the future","volume":"49","author":"O'Shaughnessy C","year":"2022","journal-title":"Rutgers L Rec"},{"key":"e_1_2_9_16_1","unstructured":"The American Presidency Project.Fact sheet: President Biden and Vice President Harris announce additional actions to reduce gun violence and save lives. [cited 2026 Mar 4]. Available from:https:\/\/www.presidency.ucsb.edu\/documents\/fact\u2010sheet\u2010president\u2010biden\u2010and\u2010vice\u2010president\u2010harris\u2010announce\u2010additional\u2010actions\u2010reduce"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.forsciint.2024.111999"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1111\/1556\u20104029.14790"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23198250"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2022.09.496"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics7020023"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAP.2010.83"},{"key":"e_1_2_9_23_1","first-page":"1","volume-title":"Proceedings of the 13th IEEE International Workshop on Information Forensics and Security (WIFS); 2021 Dec 7\u201320; Montpellier, France","author":"Li Z","year":"2021"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym10040090"},{"key":"e_1_2_9_25_1","unstructured":"LiH MaX RathoreAS LiZ AnQ SongC et\u00a0al.Image dataset for visual objects classification in 3D printing.arXivPreprint.2018.https:\/\/doi.org\/10.48550\/arXiv.1803.00391"},{"key":"e_1_2_9_26_1","first-page":"494","volume-title":"Proceedings of the 25th Asia and South Pacific Design Automation Conference (ASP\u2010DAC); 2020 Jan 13\u201316; Beijing, China","author":"Ma X","year":"2020"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.5194\/isprs\u2010archives\u2010XLII\u20104\u2010535\u20102018"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2005.27"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738542"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3020693"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12142224"},{"key":"e_1_2_9_32_1","unstructured":"Thingiverse.Digital designs for physical objects. Available from:https:\/\/www.thingiverse.com\/."},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/2945.817351"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.26833\/ijeg.987605"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116251"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSGRC.2011.5991826"},{"key":"e_1_2_9_40_1","unstructured":"O'SheaK.An introduction to convolutional neural networks.arXivPreprint.2015.https:\/\/doi.org\/10.48550\/arXiv.1511.08458"}],"container-title":["Journal of Forensic Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1556-4029.70355","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/1556-4029.70355","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1556-4029.70355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T03:52:01Z","timestamp":1790567521000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/1556-4029.70355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1111\/1556-4029.70355"],"URL":"https:\/\/doi.org\/10.1111\/1556-4029.70355","archive":["Portico"],"relation":{},"ISSN":["0022-1198","1556-4029"],"issn-type":[{"value":"0022-1198","type":"print"},{"value":"1556-4029","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"2025-07-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}