No abstract

Craniofacial superimposition, although existing for one century, is still a controversial technique within the scientific community. Objective and unbiased validation studies over a significant number of cases are required to establish a more solid picture on the reliability. However, there is lack of protocols and standards in the application of the technique leading to contradictory information concerning reliability. Instead of following a uniform methodology, every expert tends to apply his own approach to the problem, based on the available technology and deep knowledge on human craniofacial anatomy, soft tissues, and their relationships. The aim of this study was to assess the reliability of different craniofacial superimposition methodologies and the corresponding technical approaches to this type of identification. With all the data generated, some of the most representative experts in craniofacial identification joined in a discussion intended to identify and agree on the most important issues that have to be considered to properly employ the craniofacial superimposition technique. As a consequence, the consortium has produced the current manuscript, which can be considered the first standard in the field; including good and bad practices, sources of error and uncertainties, technological requirements and desirable features, and finally a common scale for the craniofacial matching evaluation. Such a document is intended to be part of a more complete framework for craniofacial superimposition, to be developed during the FP7-founded project MEPROCS, which will favour and standardize its proper application.

No abstract

No abstract

One of the major challenges in automatic classification is to deal with highly dimensional data. Several dimensionality reduction strategies, including popular feature selection metrics such as Information Gain and χ 2 , have already been proposed to deal with this situation. However, these strategies are not well suited when the data is very skewed, a common situation in real-world data sets. This occurs when the number of samples in one class is much larger than the others, causing common feature selection metrics to be biased towards the features observed in the largest class. In this paper, we propose the use of Genetic Programming (GP) to implement an aggressive, yet very effective, selection of attributes. Our GP-based strategy is able to largely reduce dimensionality, while dealing effectively with skewed data. To this end, we exploit some of the most common feature selection metrics and, with GP, combine their results into new sets of features, obtaining a better unbiased estimate for the discriminative power of each feature. Our proposal was evaluated against each individual feature selection metric used in our GP-based solution (namely, Information Gain, χ 2 , Odds-Ratio, Correlation Coefficient) using a k8 cancer-rescue mutants data set, a very unbalanced collection referring to examples of p53 protein. For this data set, our solution not only increases the efficiency of the learning algorithms, with an aggressive reduction of the input space, but also significantly increases its accuracy.