利用离子迁移谱仪和人工智能算法快速检测和分类油墨

来源: Matej Petrík et al 发布日期: 2025-02-24 访问量: 23

导读	在这项工作中，我们提出了一种使用离子迁移谱（IMS）技术和人工智能方法对不同生产商的圆珠笔油墨进行检测和分类的新方法。IMS 能够快速、灵敏、现场收集光谱数据，这些数据可以使用机器学习方法立即进行分析。在这项研究中，使用高级IMS（AIMS）仪器收集墨水数据，并应用了几个机器学习分类器（包括额外树、梯度增强、随机森林和支持向量分类器）标签: 人工智能、分类、取证、墨水、离子迁移谱仪、机器学习

Fast Detection and Classification of Ink by Ion Mobility Spectrometry and Artificial Intelligence

MATEJ PETRÍK¹, (Member, IEEE), Emanuel Mataš², Martin Sabo^1,3, Michal Ries¹，Štefan Matejčík²,
¹Faculty of Informatics and Information Technologies, Slovak University of Technology in Bratislava, Bratislava, 842 16, Slovakia
²Faculty of Mathematics, Physics and Informatics, Comenius University in Bratislava, Bratislava, 842 48, Slovakia
³MaSaTECH Ltd., Bratislava, 842 16, Slovakia
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 883116. This article was written thanks to the generous support under the Operational Program Integrated Infrastructure for the project:
"Support of research activities of Excellence laboratories STU in Bratislava ", Project no. 313021BXZ1, co-financed by the European
Regional Development Fund." The authors declare partial support by Slovak Research and Development Agency under the project No.
APVV-19-0386 and No. APVV-22-0133.

ABSTRACT

The ink can be a significant piece of evidence in the evaluation of written documents. In this work we present a new way of detection and classification of inks from ballpoint pens of different producers, using the ion mobility spectrometry (IMS) technique and artificial intelligence methods. IMS

enables fast, sensitive, on-site collection of spectrometric data, which can be immediately analyzed using machine learning methods. In this study, an Advanced IMS (AIMS) instrument was employed to gather ink data, and several machine learning classifiers (including Extra Trees, Gradient Boosting, Random Forest, and Support Vector Classifier) were applied, some of which were integrated into an ensemble voting classifier for enhanced performance. The method demonstrated a high accuracy of 95,23% in classifying inks and provided promising results in estimating the age of written text without compromising the integrity of the sample. These findings highlight the potential applications of the proposed method in forensic investigations, offering a portable, efficient, and non-destructive solution for ink analysis and ageing.

在评估书面文件时，墨水可以作为重要的取证证据。在这项工作中，我们提出了一种使用离子迁移谱（IMS）技术和人工智能方法对不同生产商的圆珠笔油墨进行检测和分类的新方法。IMS 能够快速、灵敏、现场收集光谱数据，这些数据可以使用机器学习方法立即进行分析。在这项研究中，使用高级IMS（AIMS）仪器收集墨水数据，并应用了几个机器学习分类器（包括额外树、梯度增强、随机森林和支持向量分类器），其中一些被集成到集成投票分类器中以提高性能。该方法在油墨分类方面表现出95.23%的高准确率，并在不损害样本完整性的情况下，在估计书面文本的年龄方面提供了有前景的结果。这些发现突出了所提出的方法在法医调查中的潜在应用，为油墨分析和老化提供了一种便携式、高效和非破坏性的解决方案。

INDEX TERMS： Artificial Intelligence, Classification, Forensics, Ink, Ion Mobility Spectrometer, Machine Learning

索引术语：人工智能、分类、取证、墨水、离子迁移谱仪、机器学习

···

MATERIALS AND METHODS

The spectra of ink samples were obtained using the Advanced Ion Mobility Spectrometer (AIMS) which was provided by MaSa Tech Company (www.masatech.eu).

The ink samples were prepared from pen refills, which were bought from local suppliers. The primary dataset was composed of 28 different pen refills from which the samples were recorded. The refills from 17 unique manufacturers consisted of 17 ballpoint, 10 gel-based and 1 oil-based blue pens.

CONCLUSIONS

This study highlights the innovative use of Ion Mobility Spectrometry (IMS) as a non-destructive spectrometric method for characterizing inks from various ballpoint pens. To our knowledge, this is the first application of IMS for this purpose.

本研究强调了离子迁移谱法（IMS）作为一种非破坏性光谱分析方法的创新用途，用于表征各种圆珠笔中的油墨。据我们所知，这是IMS首次用于此目的。

The primary research objective was to develop a rapid, non-invasive method to distinguish between different pen refills based on their spectrometric data, utilizing traditional machine learning techniques to maximize discrimination accuracy. Additionally, the study sought to determine the time window of sample creation, offering insights into the age of written text.

主要研究目标是开发一种快速、非侵入性的方法，根据光谱数据区分不同的笔芯，利用传统的机器学习技术最大限度地提高辨别精度。此外，该研究试图确定样本创建的时间窗口，为书面文本的年龄提供见解。

This novel approach has significant forensic applications, as it enables the fast and accurate analysis of ink evidence directly at investigation sites. The portability of IMS devices allows for real-time, on-site chemical analysis without the need for laboratory conditions, making the method particularly suitable for field use. Furthermore, the non-destructive nature of IMS ensures the integrity of evidence, which is critical in forensic scenarios.

这种新方法具有重要的法医应用，因为它能够直接在调查现场快速准确地分析墨水证据。IMS设备的便携性允许在不需要实验室条件的情况下进行实时现场化学分析，使该方法特别适合现场使用。此外，AIMS监测系统的非破坏性确保了证据的完整性，这在法医场景中至关重要。

Achieving a classification accuracy of 95.23%, this technique not only demonstrates state-of-the-art performance but also paves the way for advancements in forensic investigations. Beyond ink classification, the ability to estimate the timing of a sample’s creation further underscores its potential to contribute to solving complex forensic cases. This combination of accuracy, portability, and non-destructiveness positions IMS as a transformative tool in forensic science.

该技术实现了95.23%的分类准确率，不仅展示了最先进的性能，还为法医调查的进步铺平了道路。除了墨水分类，估计样本创建时间的能力进一步突显了其有助于解决复杂法医案件的潜力。这种准确性、便携性和非破坏性的结合使IMS成为法医学中的变革性工具。

*本文内容非商业广告，仅供专业人士参考!