A dynamic adjustment of parameters for the particle swarm optimization (PSO) utilizing an interval type-2 fuzzy inference system is proposed in this work. A fuzzy neural network with interval type-2 fuzzy number weights using S-norm and T-norm is optimized with the proposed method. A dynamic adjustment of the PSO allows the algorithm to behave better in the search for optimal results because the dynamic adjustment provides good synchrony between the exploration and exploitation of the algorithm. Results of experiments and a comparison between traditional neural networks and the fuzzy neural networks with interval type-2 fuzzy numbers weights using T-norms and S-norms are given to prove the performance of the proposed approach. For testing the performance of the proposed approach, some cases of time series prediction are applied, including the stock exchanges of Germany, Mexican, Dow-Jones, London, Nasdaq, Shanghai, and Taiwan.

Every year, new Convolutional Neural Network (CNN) architectures appear to deal with different problems in the activity of image and video recognition. These architectures usually work along the ImageNet dataset for looking for the best performance of the CNNs without taking into account the video task where they are used. This can represent a problem if the task is Human Action Recognition (HAR) in video, since the CNN architectures are pre-trained with an image dataset that can practically contain any object, while HAR problem requires consecutive frames of people doing actions. To prove the idea that using CNNs pre-trained on an image dataset does not always achieve the best performance on a video dataset and that, therefore, it is worth comparing the performance of different CNNs under similar circumstances for the HAR problem, this work proposes an analysis between eight different CNN architectures. Each one of the CNN was exclusively trained with RGB images, which were extracted from the frames of the different classes of videos of HMDB51 dataset. To make the classification of an activity in video, we average the predictions taking into account the successes. We also made some ensembles with the best performance CNNs to measure the improvement in accuracy. Our results suggest that Xception is a strong baseline model that could be used by the community to make their comparisons of their proposals more robust.

Background/Objectives: The limited availability of labeled data, particularly in the medical domain, poses a significant challenge for training accurate diagnostic models. While deep learning techniques have demonstrated notable efficacy in image-based tasks, they require large annotated datasets. In data-scarce scenarios—especially involving rare diseases—their performance deteriorates significantly. Meta-learning offers a promising alternative by enabling models to adapt quickly to new tasks using prior knowledge and only a few labeled examples. This study aims to evaluate the effectiveness of representative meta-learning models for thoracic disease classification in chest X-rays. Methods: We conduct a comparative evaluation of four meta-learning models: Prototypical Networks, Relation Networks, MAML, and FoMAML. First, we assess five backbone architectures (ConvNeXt, DenseNet-121, ResNet-50, MobileNetV2, and ViT) using a Prototypical Network. The best-performing backbone is then used across all meta-learning models for fair comparison. Experiments are performed on the ChestX-ray14 dataset under a 2-way setting with multiple k-shot configurations. Results: Prototypical Networks combined with DenseNet-121 achieved the best performance, with a recall of 68.1%, an F1-score of 67.4%, and a precision of 0.693 in the 2-way, 10-shot configuration. In a disease-specific analysis, Hernia obtains the best classification results. Furthermore, Prototypical and Relation Networks demonstrate significantly higher computational efficiency, requiring fewer FLOPs and shorter execution times than MAML and FoMAML. Conclusions: Prototype-based meta-learning, particularly with DenseNet-121, proves to be a robust and computationally efficient approach for few-shot chest X-ray disease classification. These findings highlight its potential for real-world clinical applications, especially in scenarios with limited annotated medical data.

For the last decades the work on audiorecognition has been directed to speech and music,however, an increasing interest for the classificationand recognition of acoustic events is observed for thelast years. This poses the challenge to determine theidentity of sounds, their sources, and the importanceof analysing the context of the scenario where theyact.The aim of this paper is focused on evaluatingthe robustness to retain the characteristic information ofan acoustic event against the background noise usingaudio features in the task of identifying acoustic eventsfrom a mixture of sounds that are produced in a kitchenenvironment.A new database of kitchen sounds wasbuilt by us, since in the reviewed literature there isno similar benchmark that allows us to evaluate thisissue in conditions of 3 decibels for the signal to noiseratio. In our study, we compared two methods of audiofeatures, Multiband Spectral Entropy Signature (MSES)and Mel Frequency Cepstral Coefficients (MFCC). Toevaluate the performance of both MSES and MFCC,we used different classifiers such as Similarity Distance,k-Nearest Neighbors, Support Vector Machines andArtificial Neural Networks (ANN). The results showedthat MSES supported with an ANN outperforms anyother combination of classifiers with MSES or MFCC forgetting a better score.

Sotol is a traditional distilled alcoholic beverage produced in Mexico and the United States. Unfortunately, local authorities have detected that these beverages are sometimes adulterated with toxic substances such as ethylene glycol. This illegal practice of adulteration is dangerous and can cause serious health problems for the end consumers. In this work, an alternative, reliable, and rapid method is presented for identifying the presence of ethylene glycol in sotol samples using UV-Vis spectroscopy and neural networks with an accuracy of up to 100%.