PIXE based, Machine-Learning (PIXEL) supported workflow for glass fragments classification

Kaspi, Omer; Girshevitz, Olga; Senderowitz, Hanoch

doi:10.1016/j.talanta.2021.122608

Cited by 10 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To quantify this effect, analytical methods that used whole samples (SEM-EDS, PIXE, and PIGE) measured them in two orientations corresponding to the surface and bulk (specimen that had a smooth surface likely originate from the surface of the glass, while those with ruptured surfaces likely originate from the bulk of the glass). The previous study reported a negligible effect of corrosion on the performances of classification models . INAA and LA-ICP-MS are bulk analysis techniques; thus, any surface effects such as corrosion would be insignificant.…”

Section: Methodsmentioning

confidence: 93%

“…In sample measurement , each sample was analyzed for its elemental composition, and each element concentration was expressed in units of parts per million (ppm). Elemental composition measurements require homogeneity which was previously demonstrated . One factor that may compromise sample homogeneity is corrosion, known to occur on glass surfaces with time.…”

Section: Methodsmentioning

confidence: 97%

“…The workflow employed in this work largely follows the one used in our previous works , (Figure ). In sample acquisition , 48 glass specimens from 13 different car models from 10 car manufacturers were collected and recorded.…”

Section: Methodsmentioning

confidence: 99%

“…To date, there are several methods for analyzing glass specimens, including refraction index (RI), − physical attribute matching, and electron microscopy. − However, these methods suffer from several deficiencies as previously discussed . Another analytical approach to study glass fragments, which is gaining popularity among law enforcement agencies, , is based on elemental analysis.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Toward Developing Techniques─Agnostic Machine Learning Classification Models for Forensically Relevant Glass Fragments

Kaspi

Israelsohn-Azulay²,

Zidon³

et al. 2022

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Glass fragments found in crime scenes may constitute important forensic evidence when properly analyzed, for example, to determine their origin. This analysis could be greatly helped by having a large and diverse database of glass fragments and by using it for constructing reliable machine learning (ML)-based glass classification models. Ideally, the samples that make up this database should be analyzed by a single accurate and standardized analytical technique. However, due to differences in equipment across laboratories, this is not feasible. With this in mind, in this work, we investigated if and how measurement performed at different laboratories on the same set of glass fragments could be combined in the context of ML. First, we demonstrated that elemental analysis methods such as particle-induced X-ray emission (PIXE), laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS), scanning electron microscopy with energy-dispersive X-ray spectrometry (SEM-EDS), particle-induced Gamma-ray emission (PIGE), instrumental neutron activation analysis (INAA), and prompt Gamma-ray neutron activation analysis (PGAA) could each produce lab-specific ML-based classification models. Next, we determined rules for the successful combinations of data from different laboratories and techniques and demonstrated that when followed, they give rise to improved models, and conversely, poor combinations will lead to poor-performing models. Thus, the combination of PIXE and LA-ICP-MS improves the performances by ∼10–15%, while combining PGAA with other techniques provides poorer performances in comparison with the lab-specific models. Finally, we demonstrated that the poor performances of the SEM-EDS technique, still in use by law enforcement agencies, could be greatly improved by replacing SEM-EDS measurements for Fe and Ca by PIXE measurements for these elements. These findings suggest a process whereby forensic laboratories using different elemental analysis techniques could upload their data into a unified database and get reliable classification based on lab-agnostic models. This in turn brings us closer to a more exhaustive extraction of information from glass fragment evidence and furthermore may form the basis for international-wide collaboration between law enforcement agencies.

show abstract

Section: Methodsmentioning

confidence: 93%

Section: Methodsmentioning

confidence: 97%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Toward Developing Techniques─Agnostic Machine Learning Classification Models for Forensically Relevant Glass Fragments

Kaspi

Israelsohn-Azulay²,

Zidon³

et al. 2022

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

show abstract

“…A paper by Kaspi et al discussed the use of the combination of PIXE to obtain analytical data followed by a machine learning algorithm to support the workflow for glass fragment classification. 338 The algorithm was written in Python and included Box plots, PCA, KNN, cluster analysis and random forest. As with many algorithms of this kind, once built, the model had to be trained by inserting data of known origin.…”

Section: Forensic Analysesmentioning

confidence: 99%

Atomic spectrometry update: review of advances in the analysis of metals, chemicals and materials

Carter¹,

Clough

Fisher

et al. 2022

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

A comparison between 2D and 3D descriptors in QSAR modeling based on bio‐active conformations

Senderowitz

Bahia

Kaspi

et al. 2023

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

QSAR models are widely and successfully used in many research areas. The success of such models highly depends on molecular descriptors typically classified as 1D, 2D, 3D, or 4D. While 3D information is likely important, e. g., for modeling ligand-protein binding, previous comparisons between the performances of 2D and 3D descriptors were inconclusive. Yet in such comparisons the modeled ligands were not necessarily represented by their bioactive conformations. With this in mind, we mined the PDB for sets of protein-ligand complexes sharing the same protein for which uniform activity data were reported. The results, totaling 461 structures spread across six series were compiled into a carefully curated, first of its kind dataset in which each ligand is represented by its bioactive conformation. Next, each set was characterized by 2D, 3D and 2D + 3D descriptors and modeled using three machine learning algorithms, namely, k-Nearest Neighbors, Random Forest and Lasso Regression. Models' performances were evaluated on external test sets derived from the parent datasets either randomly or in a rational manner. We found that many more significant models were obtained when combining 2D and 3D descriptors. We attribute these improvements to the ability of 2D and 3D descriptors to code for different, yet complementary molecular properties.

show abstract

PIXE based, Machine-Learning (PIXEL) supported workflow for glass fragments classification

Cited by 10 publications

References 23 publications

Toward Developing Techniques─Agnostic Machine Learning Classification Models for Forensically Relevant Glass Fragments

Toward Developing Techniques─Agnostic Machine Learning Classification Models for Forensically Relevant Glass Fragments

Atomic spectrometry update: review of advances in the analysis of metals, chemicals and materials

A comparison between 2D and 3D descriptors in QSAR modeling based on bio‐active conformations

Contact Info

Product

Resources

About