Alicia Morales-Reyes

Accurate atomic parameters are essential for reliable spectral synthesis, particularly in the ultraviolet range, where line blending and parameter degeneracy pose significant challenges. In this feasibility test, we apply different optimization techniques to calibrate the atomic data of central wavelength, oscillator strength, and damping parameters by minimizing the difference between the synthetic and reference spectra. We compare the performance of genetic algorithm (GA), differential evolution, particle swarm optimization, cross-entropy algorithm, and covariance matrix adaptation evolution strategy (CMA-ES). Our results show that GA and CMA-ES consistently outperform the other algorithms. We assessed the accuracy of the optimized parameters using their standard deviation from the algorithm executions. Using this criterion, a significant fraction (63 per cent of the central wavelengths and 48 per cent of oscillator strengths) of the strongest lines were recovered accurately. Within this subset, our approach yielded in some cases uncertainties comparable to or smaller than those reported by the NIST (National Institute of Standards and Technology) Atomic Spectra Database and the Vienna Atomic Line Database. In contrast, Van der Waals and Stark broadening parameters were severely affected by parameter degeneracy. These findings establish GA and CMA-ES as a reliable optimization method for this high-dimensional problem.

Genetic programming (GP) and fuzzy logic to automatically segment mammography images. GP allows the evolution of optimized segmentation models, guided by a fuzzy logic-based fitness function that incorporates medical criteria to improve the consistency and accuracy of the segmentation process. Unlike conventional approaches, this function optimizes the segmentation and provides a descriptive representation of the breast tissue, allowing a closer evaluation to that performed by specialists. The proposed method was evaluated in the INbreast and BCDR databases, obtaining a Jaccard index of 0.82 and 0.78, respectively, and a comparative analysis was performed using ROC curves, reaching an AUC of 0.91 in INbreast and 0.89 in BCDR, demonstrating the model’s ability to discriminate between fibroglandular and fat tissue. Its performance was compared with state-of-the-art methods, such as LIBRA, hybrid segmentation with Fuzzy C-Means, and NASGP-Net, showing that integrating fuzzy logic in genetic programming to lead the search allows competitive results with a lower computational burden. These results demonstrate the impact of fuzzy fitness functions in the evolution of segmentation models, highlighting the effectiveness of this approach in improving the segmentation and classification of medical images, in addition to the descriptive capabilities inherent to the fuzzy fitness function.

We introduce TurboGP, a Genetic Programming (GP) library fully written in Python and specifically designed for machine learning tasks. TurboGP implements modern features not available in other GP implementations, such as island and cellular population schemes, different types of genetic operations (migration, protected crossovers), online learning, among other features. TurboGP's most distinctive characteristic is its native support for different types of GP nodes to allow different abstraction levels, this makes TurboGP particularly useful for processing a wide variety of data sources.

We propose a novel approach for the challenge of designing less complex yet highly effective convolutional neural networks (CNNs) through the use of cartesian genetic programming (CGP) for neural architecture search (NAS). Our approach combines real-based and block-chained CNNs representations based on CGP for optimization in the continuous domain using multi-objective evolutionary algorithms (MOEAs). Two variants are introduced that differ in the granularity of the search space they consider. The proposed CGP-NASV1 and CGP-NASV2 algorithms were evaluated using the non-dominated sorting genetic algorithm II (NSGA-II) on the CIFAR-10 and CIFAR-100 datasets. The empirical analysis was extended to assess the crossover operator from differential evolution (DE), the multi-objective evolutionary algorithm based on decomposition (MOEA/D) and S metric selection evolutionary multi-objective algorithm (SMS-EMOA) using the same representation. Experimental results demonstrate that our approach is competitive with state-of-the-art proposals in terms of classification performance and model complexity.