Search

The Internet of Medical Things (IoMT) has dramatically benefited medical professionals that patients and physicians can access from all regions. Although the automatic detection and prediction of diseases such as melanoma and leukemia is still being researched and studied in IoMT, existing approaches are not able to achieve a high degree of efficiency. Thus, with a new approach that provides better results, patients would access the adequate treatments earlier and the death rate would be reduced. Therefore, this paper introduces an IoMT proposal for medical images classification that may be used anywhere, i.e. it is an ubiquitous approach. It was design in two stages: first, we employ a Transfer Learning (TL)-based method for feature extraction, which is carried out using MobileNetV3; second, we use the Chaos Game Optimization (CGO) for feature selection, with the aim of excluding unnecessary features and improving the performance, which is key in IoMT. Our methodology was evaluated using ISIC-2016, PH2, and Blood-Cell datasets. The experimental results indicated that the proposed approach obtained an accuracy of 88.39% on ISIC-2016, 97.52% on PH2, and 88.79% on Blood-cell. Moreover, our approach had successful performances for the metrics employed compared to other existing methods., Comment: 22 pages, 12 figures, journal

Federated learning is a very convenient approach for scenarios where (i) the exchange of data implies privacy concerns and/or (ii) a quick reaction is needed. In smart healthcare systems, both aspects are usually required. In this paper, we work on the first scenario, where preserving privacy is key and, consequently, building a unique and massive medical image data set by fusing different data sets from different medical institutions or research centers (computation nodes) is not an option. We propose an ensemble federated learning (EFL) approach that is based on the following characteristics: First, each computation node works with a different data set (but of the same type). They work locally and apply an ensemble approach combining eight well-known CNN models (densenet169, mobilenetv2, xception, inceptionv3, vgg16, resnet50, densenet121, and resnet152v2) on Chest X-ray images. Second, the best two local models are used to create a local ensemble model that is shared with a central node. Third, the ensemble models are aggregated to obtain a global model, which is shared with the computation nodes to continue with a new iteration. This procedure continues until there are no changes in the best local models. We have performed different experiments to compare our approach with centralized ones (with or without an ensemble approach)\color{black}. The results conclude that our proposal outperforms these ones in Chest X-ray images (achieving an accuracy of 96.63\%) and offers very competitive results compared to other proposals in the literature., Comment: 15 pages, 9 figures, journal

Pneumonia is a life-threatening lung infection resulting from several different viral infections. Identifying and treating pneumonia on chest X-ray images can be difficult due to its similarity to other pulmonary diseases. Thus, the existing methods for predicting pneumonia cannot attain substantial levels of accuracy. Therefore, this paper presents a computer-aided classification of pneumonia, coined as Ensemble Learning (EL), to simplify the diagnosis process on chest X-ray images. Our proposal is based on Convolutional Neural Network (CNN) models, which are pre-trained CNN models that have been recently employed to enhance the performance of many medical tasks instead of training CNN models from scratch. We propose to use three well-known CNN pre-trained (DenseNet169, MobileNetV2 and Vision Transformer) using the ImageNet database. Then, these models are trained on the chest X-ray data set using fine-tuning. Finally, the results are obtained by combining the extracted features from these three models during the experimental phase. The proposed EL approach outperforms other existing state-of-the-art methods, and it obtains an accuracy of 93.91% and a F1-Score of 93.88% on the testing phase., Comment: 14 pages, 4 figures, journal

Metaheuristics algorithms are designed to find approximate solutions for challenging optimization problems. The success of the algorithm over a given optimization task relies on the suitability of its search heuristics for the problem-domain. Thus, the design of custom metaheuristic algorithms leads to more accurate solutions. Hyper-heuristics (HH) are important tools commonly used to select low-level heuristics (LLHs) to solve a specific problem. HH are able to acquire knowledge from the problems where they are used. However, as other artificial intelligence tools it is necessary to identify how the knowledge affects the performance of the algorithm. One way to generate such knowledge is to capture interactions between variables using probabilistic graphical models such as Bayesian networks (BN) in conjunction with estimation of distribution algorithms (EDA). This article presents a method based on that used an EDA based on BN as a high-level selection mechanism for HH called Hyper-heuristic approach based on Bayesian learning and evolutionary operators (HHBNO). Here the knowledge is extracted form BN to evolve the sequences of LLHs in an online learning process by exploring the inter-dependencies among the LLHs. The proposes approach is tested over CEC’17 set of benchmark function of single-objective real-parameter optimization. Statical tests verifies that the HHBNO presents competitive results in comparison with other metaheuristic algorithms with high performance in terms of convergence. The generated BN is further visually investigated to display the acquired knowledge during the evolutionary process, and it is constructed with the probabilities of each LLHs.