On the use of Aggregation Operators to improve Human Identification using Dental Records
arXiv:2603.23003v1 Announce Type: new Abstract: The comparison of dental records is a standardized technique in forensic dentistry used to speed up the identification of individuals in multiple-comparison scenarios. Specifically, the odontogram comparison is a procedure to compute criteria that will be used to perform a ranking. State-of-the-art automatic methods either make use of simple techniques, without utilizing the full potential of the information obtained from a comparison, or their internal behavior is not known due to the lack of peer-reviewed publications. This work aims to design aggregation mechanisms to automatically compare pairs of dental records that can be understood and validated by experts, improving the current methods. To do so, we introduce different aggregation approaches using the state-of-the-art codification, based on seven different criteria. In particular, we study the performance of i) data-driven lexicographical order-based aggregations, ii) well-known
arXiv:2603.23003v1 Announce Type: new Abstract: The comparison of dental records is a standardized technique in forensic dentistry used to speed up the identification of individuals in multiple-comparison scenarios. Specifically, the odontogram comparison is a procedure to compute criteria that will be used to perform a ranking. State-of-the-art automatic methods either make use of simple techniques, without utilizing the full potential of the information obtained from a comparison, or their internal behavior is not known due to the lack of peer-reviewed publications. This work aims to design aggregation mechanisms to automatically compare pairs of dental records that can be understood and validated by experts, improving the current methods. To do so, we introduce different aggregation approaches using the state-of-the-art codification, based on seven different criteria. In particular, we study the performance of i) data-driven lexicographical order-based aggregations, ii) well-known fuzzy logic aggregation methods and iii) machine learning techniques as aggregation mechanisms. To validate our proposals, 215 forensic cases from two different populations have been used. The results obtained show how the use of white-box machine learning techniques as aggregation models (average ranking from 2.02 to 2.21) are able to improve the state-of-the-art (average ranking of 3.91) without compromising the explainability and interpretability of the method.
Executive Summary
This article proposes the use of aggregation operators to improve human identification using dental records. The authors introduce various aggregation approaches, including data-driven lexicographical order-based aggregations, fuzzy logic aggregation methods, and machine learning techniques. The results show that white-box machine learning techniques can improve the state-of-the-art method without compromising explainability and interpretability. The study uses 215 forensic cases from two different populations to validate the proposals, achieving an average ranking of 2.02 to 2.21, outperforming the current state-of-the-art average ranking of 3.91.
Key Points
- ▸ The article aims to design aggregation mechanisms for automatic comparison of dental records
- ▸ Seven different criteria are used for the aggregation approaches
- ▸ Machine learning techniques show improved performance over the state-of-the-art method
Merits
Improved Accuracy
The proposed aggregation mechanisms demonstrate improved accuracy in human identification using dental records
Explainability and Interpretability
The use of white-box machine learning techniques ensures that the method remains explainable and interpretable
Demerits
Limited Dataset
The study uses a limited dataset of 215 forensic cases, which may not be representative of all possible scenarios
Lack of Peer-Reviewed Publications
The article highlights the lack of peer-reviewed publications on internal behavior of state-of-the-art automatic methods, which may limit the understanding of the proposed aggregation mechanisms
Expert Commentary
The article presents a significant contribution to the field of forensic dentistry, demonstrating the potential of aggregation operators to improve human identification using dental records. The use of machine learning techniques, in particular, shows promise in achieving more accurate results while maintaining explainability and interpretability. However, further research is needed to validate the proposed mechanisms using larger and more diverse datasets. Additionally, the article highlights the need for more peer-reviewed publications on the internal behavior of state-of-the-art automatic methods, which can facilitate a deeper understanding of the proposed aggregation mechanisms.
Recommendations
- ✓ Further research should be conducted to validate the proposed aggregation mechanisms using larger and more diverse datasets
- ✓ The development of more transparent and explainable machine learning models can facilitate the adoption of these methods in forensic dentistry
Sources
Original: arXiv - cs.AI
