Swarm intelligence techniques have been created to respond to theoretical and practical global optimization problems. This paper puts forward an enhanced version of the firefly algorithm that corrects the acknowledged drawbacks of the original method, by an explicit exploration mechanism and a chaotic local search strategy. The resulting augmented approach was theoretically tested on two sets of bound-constrained benchmark functions from the CEC suites and practically validated for automatically selecting the optimal dropout rate for the regularization of deep neural networks. Despite their successful applications in a wide spectrum of different fields, one important problem that deep learning algorithms face is overfitting. The traditional way of preventing overfitting is to apply regularization; the first option in this sense is the choice of an adequate value for the dropout parameter. In order to demonstrate its ability in finding an optimal dropout rate, the boosted version of the firefly algorithm has been validated for the deep learning subfield of convolutional neural networks, with respect to five standard benchmark datasets for image processing: MNIST, Fashion-MNIST, Semeion, USPS and CIFAR-10. The performance of the proposed approach in both types of experiments was compared with other recent state-of-the-art methods. To prove that there are significant improvements in results, statistical tests were conducted. Based on the experimental data, it can be concluded that the proposed algorithm clearly outperforms other approaches.

Rapid developments in Internet of Things (IoT) systems have led to a wide integration of such systems into everyday life. Systems for active real-time monitoring are especially useful in areas where rapid action can have a significant impact on outcomes such as healthcare. However, a major challenge persists within IoT that limit wider integration. Sustainable healthcare supported by the IoT must provide organized healthcare to the population, without compromising the environment. Security plays a major role in the sustainability of IoT systems, therefore detecting and taking timely action is one step in overcoming the sustainability challenges. This work tackles security challenges head-on through the use of machine learning algorithms optimized via a modified Firefly algorithm for detecting security issues in IoT devices used for Healthcare 4.0. Metaheuristic solutions have contributed to sustainability in various areas as they can solve nondeterministic polynomial time-hard problem (NP-hard) problems in realistic time and with accuracy which are paramount for sustainable systems in any sector and especially in healthcare. Experiments on a synthetic dataset generated by an advanced configuration tool for IoT structures are performed. Also, multiple well-known machine learning models were used and optimized by introducing modified firefly metaheuristics. The best models have been subjected to SHapley Additive exPlanations (SHAP) analysis to determine the factors that contribute to occurring issues. Conclusions from all the performed testing and comparisons indicate significant improvements in the formulated problem.

We live in a period when smart devices gather a large amount of data from a variety of sensors and it is often the case that decisions are taken based on them in a more or less autonomous manner. Still, many of the inputs do not prove to be essential in the decision-making process; hence, it is of utmost importance to find the means of eliminating the noise and concentrating on the most influential attributes. In this sense, we put forward a method based on the swarm intelligence paradigm for extracting the most important features from several datasets. The thematic of this paper is a novel implementation of an algorithm from the swarm intelligence branch of the machine learning domain for improving feature selection. The combination of machine learning with the metaheuristic approaches has recently created a new branch of artificial intelligence called learnheuristics. This approach benefits both from the capability of feature selection to find the solutions that most impact on accuracy and performance, as well as the well known characteristic of swarm intelligence algorithms to efficiently comb through a large search space of solutions. The latter is used as a wrapper method in feature selection and the improvements are significant. In this paper, a modified version of the salp swarm algorithm for feature selection is proposed. This solution is verified by 21 datasets with the classification model of K-nearest neighborhoods. Furthermore, the performance of the algorithm is compared to the best algorithms with the same test setup resulting in better number of features and classification accuracy for the proposed solution. Therefore, the proposed method tackles feature selection and demonstrates its success with many benchmark datasets.

Monitoring heart electrical activity is an effective way of detecting existing and developing conditions. This is usually performed as a non-invasive test using a network of up to 12 sensors (electrodes) on the chest and limbs to create an electrocardiogram (ECG). By visually observing these readings, experienced professionals can make accurate diagnoses and, if needed, request further testing. However, the training and experience needed to make accurate diagnoses are significant. This work explores the potential of recurrent neural networks for anomaly detection in ECG readings. Furthermore, to attain the best possible performance for these networks, training parameters, and network architectures are optimized using a modified version of the well-established particle swarm optimization algorithm. The performance of the optimized models is compared to models created by other contemporary optimizers, and the results show significant potential for real-world applications. Further analyses are carried out on the best-performing models to determine feature importance.

The agriculture sector, once reliant only on external inputs for increased yields, faces repercussions of diminished natural systems and significant environmental impact. High-precision agriculture aims to curb excessive usage of fertilizers and pesticides while prioritizing sustainability. Modern technologies can shape decisions toward the betterment of soil health, plant protection, and yield enhancement. Predictive models employing machine learning aid farmers in crop performance estimation, disease detection, soil health assessment, and yield prediction among others. These insights inform field operations, logistics, and contract negotiations. Leveraging machinery data, weather data, and drone imagery using machine learning can help us refine farming practices. Recurrent neural networks (RNN) can aid in various farming challenges like plant stress detection and irrigation. Yet, challenges persist in optimizing hyperparameters, a task we tackled using the nature-inspired crayfish optimization algorithm (COA) adapted to tune echo state networks (ESN) for multivariate time series forecasting of crop yield. This study demonstrates the utility of machine learning in agriculture, enabling yield assessment for improved sustainability.

The problem of fake news on the Internet is not new. However, in the case of a global pandemic, this kind of misinformation can be dangerous, confusing, and costly in terms of the loss of human lives. The ongoing COVID-19 pandemic has unfortunately shown the significant and remarkable spread of fake news, concerning the disease itself, vaccination, number of deaths, and so on. It is necessary to develop an effective algorithm that will be able to detect COVID-19 misinformation and help scientists to easily separate fake from true news. The research presented in this paper proposes an arithmetic optimization algorithm (AOA) - based approach that can improve the classification results by reducing the number of features and achieve high accuracy. The AOA has been utilized as a wrapper feature selection. The obtained simulation results were subject to a comparative analysis with both world-class classifiers and other nature-inspired evolutionary approaches. The results of the simulation indicate better performance of the proposed approach with AOA over other algorithms and demonstrate that it obtains superior accuracy.