The accurate and efficient segmentation of coronary arteries in X-ray angiograms represents an essential task for computer-aided diagnosis. This paper presents a new multiscale Gaussian-matched filter (MGMF) based on artificial neural networks. The proposed method consists of two different stages. In the first stage, MGMF is used for detecting vessel-like structures while reducing image noise. The results of MGMF are compared with those obtained using six GMF-based detection methods in terms of the area (Az) under the receiver operating characteristic (ROC) curve. In the second stage, ten thresholding methods of the state of the art are compared in order to classify the magnitude of the multiscale Gaussian response into vessel and nonvessel pixels, respectively. The accuracy measure is used to analyze the segmentation methods, by comparing the results with a set of 100 X-ray coronary angiograms, which were outlined by a specialist to form the ground truth. Finally, the proposed method is compared with seven state-of-the-art vessel segmentation methods. The vessel detection results using the proposed MGMF method achieved an Az=0.9357 with a training set of 50 angiograms and Az=0.9362 with the test set of 50 images. In addition, the segmentation results using the intraclass variance thresholding method provided a segmentation accuracy of 0.9568 with the test set of coronary angiograms.

There are various issues that limit the development and deployment of new software solutions in cancer image analysis research. In this paper we discuss some of these and propose a framework design based on cloud computing concepts, Microsoft technologies, existing middleware and imaging toolkits. Furthermore, we address some of these issues by introducing collaborative visual tools for visual input data and multi-user interactions.

In this paper, a gas sensing system based on a conventional absorption technique using a single-mode-fiber supercontinuum source (SMF-SC) is presented. The SC source was implemented by channeling pulses from a microchip laser into a one kilometer long single-mode fiber (SMF), obtaining a flat high-spectrum with a bandwidth of up to 350 nm in the region from 1350 to 1700 nm, and high stability in power and wavelength. The supercontinuum radiation was used for simultaneously sensing water vapor and acetylene gas in the regions from 1350 to 1420 nm and 1510 to 1540 nm, respectively. The experimental results show that the absorption peaks of acetylene have a maximum depth of approximately 30 dB and contain about 60 strong lines in the R and P branches, demonstrating a high sensitivity of the sensing setup to acetylene. Finally, to verify the experimental results, the experimental spectra are compared to simulations obtained from the Hitran database. This shows that the implemented system can be used to develop sensors for applications in broadband absorption spectroscopy and as a low-cost absorption spectrophotometer of multiple gases.

Convolutional neural networks (CNNs) are widely used for image classification; however, setting the appropriate hyperparameters before training is subjective and time consuming, and the search space is not properly explored. This paper presents a novel method for the automatic neural architecture search based on an estimation of distribution algorithm (EDA) for binary classification problems. The hyperparameters were coded in binary form due to the nature of the metaheuristics used in the automatic search stage of CNN architectures which was performed using the Boltzmann Univariate Marginal Distribution algorithm (BUMDA) chosen by statistical comparison between four metaheuristics to explore the search space, whose computational complexity is O($2^{29}$). Moreover, the proposed method is compared with multiple state-of-the-art methods on five databases, testing its efficiency in terms of accuracy and F1-score. In the experimental results, the proposed method achieved an F1-score of 97.2%, 98.73%, 97.23%, 98.36%, and 98.7% in its best evaluation, better results than the literature. Finally, the computational time of the proposed method for the test set was ≈0.6 s, 1 s, 0.7 s, 0.5 s, and 0.1 s, respectively.

Las habilidades relacionadas con el pensamiento computacional y el aprendizaje automático son fundamentales en la actualidad, por lo que es necesario trabajarlas desde edades tempranas. Para ello, existen diversas herramientas diseñadas para fomentar dichas habilidades en niñas y niños de manera didáctica, visual, y entretenida. Estas herramientas pueden clasificarse en gratuitas y de pago. En este trabajo nos enfocamos en las plataformas gratuitas más reconocidas en el área, como Scratch, Code.org, Teachable Machine, y Machine Learning for Kids, con el propósito de desarrollar actividades que promuevan el pensamiento computacional y el aprendizaje automático en estudiantes de primaria. El objetivo principal fue crear actividades digitales interactivas utilizando estas plataformas, que permitan a niñas y niños aprender conceptos clave de aprendizaje automático y pensamiento computacional. Para la planeación, diseño, y ejecución de las actividades, se utilizó la metodología SCRUM, organizando el trabajo en sprints y asignando tareas específicas a lo largo de cada iteración. Esta metodología permitió una mejor gestión del tiempo, priorización de actividades, revisión continua y adaptación según la retroalimentación recibida. Como resultado, se seleccionaron herramientas de aprendizaje de programación y de inteligencia artificial para niños y se diseñaron un conjunto de actividades de programación por bloques y actividades de clasificación automática enfocadas en temas de ciencia. Estas actividades están listas para ser implementadas en sesiones de trabajo con niñas y niños.

Nowadays, computational thinking plays a very important role in everyday life, which is why schools have sought to incorporate programming into their curricula to support its development. In this research, we focused on generating learning paths for children. To achieve this, we developed a tool that allowed us to capture data, which was then processed and analyzed using fuzzy logic. As a result, we obtained the next exercise each user should solve, which helped us create personalized learning paths for every user on our platform. Smart citations: https://scite.ai/reports/10.61467/2007.1558.2026.v17i1.1170Dimensions.Open Alex.