Convolutional Neural Networks (CNNs) have shown a competitive performance in medical imaging applications, such as image segmentation. However, choosing an existing architecture capable of adapting to a specific dataset is challenging and requires design expertise. Neural Architecture Search (NAS) is employed to overcome these limitations. NAS uses techniques to design the Neural Networks architecture. Typically, the models’ weights optimization is carried out using a continuous loss function, unlike model topology optimization, which is highly influenced by the specific problem. Genetic Programming (GP) is an Evolutionary Algorithm (EA) capable of adapting to the topology optimization problem of CNNs by considering the attributes of its representation. A tree representation can express complex connectivity and apply variation operations. This paper presents a tree-based GP algorithm for evolving CNNs based on the well-known U-Net architecture producing compact and flexible models for medical image segmentation across multiple domains. This proposal is called Neural Architecture Search / Genetic Programming / U-Net (NASGP-Net). NASGP-Net uses a cell-based encoding and U-Net architecture as a backbone to construct CNNs based on a hierarchical arrangement of primitive operations. Our experiments indicate that our approach can produce remarkable segmentation results with fewer parameters regarding fixed architectures. Moreover, NASGP-Net presents competitive results against NAS methods. Finally, we observed notable performance improvements based on several evaluation metrics, including Dice similarity coefficient (DSC), Intersection over union (IoU), and Hausdorff Distance (HD).

Agriculture and raising livestock are human activities highly affected by drought. In Mexico, the Veracruz territory is seriously affected by this phenomenon. Our study had two objectives: (1) to analyze the drought evolution through the Standardized Precipitation Index (SPI) and the maximum temperature in the central zone of the state of Veracruz for the period 1980–2018; and (2) to describe the relationship between the yield of corn grain and cattle, and the SPI, in the study area. The methodology consisted of calculating the SPI to estimate the drought conditions in the mentioned area. Subsequently, we determined the relationship of these conditions with the maximum temperature increase and the presence of El Niño/La Niña events. The results showed that the drought has intensified during 1980–2018, having a presence in almost 50% of the area. Additionally, the maximum temperature increased by approximately 6 °C. As a result, the cultivation of corn grain under rain conditions showed reductions in 48% of the analyzed municipalities. Concerning livestock variables, lower reductions were reported (42–32%) for the same period. Therefore, we can conclude that the drought has intensified in recent years due to an increase in the maximum temperature and El Niño/La Niña events, and these factors have had a higher impact on the agricultural sector.

Cervical Cytology or Pap Smear is the most popular technique for pre-diagnosis of cervical cancer. However, this technique has a high rate of false negative. As a consequence, it is necessary to complement it with other tests like Colposcopy. In some studies about the colposcopy test, it has been proposed that temporal changes intrinsic to the colposcopic image can be used to automatically characterize cervical lesions. In this document, a methodology to segment colposcopic images based on these temporal changes produced by the acetowhite reaction is presented in order to support to the colposcopist in the early detection of cervical cancer. This methodology consists in two stages: (1) a preprocessing stage, where several steps (extraction of time series, dimensionality reduction, classification process and a post-processing stage) are done to decrease problems or noise (specular reflection and keratosis) that can be seen as the acetowhite reaction, and (2) a segmentation stage where the active contour model (Snake) is used, changing the greedy search mechanism by a global search mechanism (evolutionary programming). The experiments were developed using only one colposcopic image and all the image sequence extracted from the colposcopy process. Results show that our methodology is a competitive tool to support to the colposcopist in the early detection of cervical cancer, providing one step towards the decrease of the mortality rate of this disease.

In this work, an adaptive algorithm for the symbolic discretization of time series is introduced. This approach, called MODiTS, consists of defining a different alphabet vector for each word segment. The number of alphabets and the word size are optimized automatically using a well-known multi-objective algorithm: Non-dominated Sorting Genetic Algorithm (NSGA-II). NSGA-II was adapted to help find the appropriate symbolic representation scheme for each temporal database based on the minimization of three objective functions (Entropy, Complexity, and Compression). Each scheme was evaluated based on the misclassification error rate calculated by means of the Decision Tree, which also provides relevant information about the regions, relationships or patterns within each database, in addition to its function as a descriptive tool to help understand temporal data. Our proposal was compared with two symbolic discretization algorithms: Symbolic Aggregate approximation (SAX), and Evolutionary Programming (EP). The statistical results suggest that our algorithm is a useful tool in finding competitive symbolic representation schemes with a lower dimensionality reduction rate and an acceptable level of classification error.