Enrique Bermejo

Age‐at‐death estimation is an arduous task in human identification based on characteristics such as appearance, morphology or ossification patterns in skeletal remains. This process is performed manually, although in recent years there have been several studies that attempt to automate it. One of the most recent approaches involves considering interpretable machine learning methods, obtaining simple and easily understandable models. The ultimate goal is not to fully automate the task but to obtain an accurate model supporting the forensic anthropologists in the age‐at‐death estimation process. We propose a semi‐automatic method for age‐at‐death estimation based on nine pubic symphysis traits identified from Todd's pioneering method. Genetic programming is used to learn simple mathematical expressions following a symbolic regression process, also developing feature selection. Our method follows a component‐scoring approach where the values of the different traits are evaluated by the expert and aggregated by the corresponding mathematical expression to directly estimate the numeric age‐at‐death value. Oversampling methods are considered to deal with the strongly imbalanced nature of the problem. State‐of‐the‐art performance is achieved thanks to an interpretable model structure that allows us to both validate existing knowledge and extract some new insights in the discipline.

Image registration (IR) is an extended and important problem in computer vision. It involves the transformation of different sets of image data having a shared content into a common coordinate system. Specifically, we will deal with the 3D intensity-based medical IR problem where the intensity distribution of the images is considered, one of the most complex and time consuming variants. The limitations of traditional IR methods have boomed the application of evolutionary and metaheuristic-based approaches to solve the problem, aiming to improve the performance of existing methods both in terms of accuracy and efficiency. In this contribution, we consider the use of a recently proposed bio-inspired meta-heuristic: the Coral Reef Optimization Algorithm (CRO). This novel algorithm simulates the natural phenomena underlying a coral reef, where different corals grow, reproduce and fight with other corals for space in the colony. CRO has recently obtained promising results in different real-world applications and we think its operation mode can properly cope with the 3D intensity-based medical IR problem. We adapt the algorithm to the real-coding problem nature and run an experimental setup tackling sixteen real-world problem instances. The new proposal is benchmarked with recent, state-of-the-art IR techniques. The results show that the CRO-based overcomes the state-of-the-art results in terms of its robustness and time efficiency.