Developing countries have had numerous obstacles in diagnosing the COVID-19 worldwide pandemic since its emergence. One of the most important ways to control the spread of this disease begins with early detection, which allows that isolation and treatment could perhaps be started. According to recent results, chest X-ray scans provide important information about the onset of the infection, and this information may be evaluated so that diagnosis and treatment can begin sooner. This is where artificial intelligence collides with skilled clinicians’ diagnostic abilities. The suggested study’s goal is to make a contribution to battling the worldwide epidemic by using a simple convolutional neural network (CNN) model to construct an automated image analysis framework for recognizing COVID-19 afflicted chest X-ray data. To improve classification accuracy, fully connected layers of simple CNN were replaced by the efficient extreme gradient boosting (XGBoost) classifier, which is used to categorize extracted features by the convolutional layers. Additionally, a hybrid version of the arithmetic optimization algorithm (AOA), which is also developed to facilitate proposed research, is used to tune XGBoost hyperparameters for COVID-19 chest X-ray images. Reported experimental data showed that this approach outperforms other state-of-the-art methods, including other cutting-edge metaheuristics algorithms, that were tested in the same framework. For validation purposes, a balanced X-ray images dataset with 12,000 observations, belonging to normal, COVID-19 and viral pneumonia classes, was used. The proposed method, where XGBoost was tuned by introduced hybrid AOA, showed superior performance, achieving a classification accuracy of approximately 99.39% and weighted average precision, recall and F1-score of 0.993889, 0.993887 and 0.993887, respectively.

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.

Software is increasingly vital, with automated systems regulating critical functions. As development demands grow, manual code review becomes more challenging, often making testing more time-consuming than development. A promising approach to improving defect detection at the source code level is the use of artificial intelligence combined with natural language processing (NLP). Source code analysis, leveraging machine-readable instructions, is an effective method for enhancing defect detection and error prevention. This work explores source code analysis through NLP and machine learning, comparing classical and emerging error detection methods. To optimize classifier performance, metaheuristic optimizers are used, and algorithm modifications are introduced to meet the study’s specific needs. The proposed two-tier framework uses a convolutional neural network (CNN) in the first layer to handle large feature spaces, with AdaBoost and XGBoost classifiers in the second layer to improve error identification. Additional experiments using term frequency–inverse document frequency (TF-IDF) encoding in the second layer demonstrate the framework’s versatility. Across five experiments with public datasets, the accuracy of the CNN was 0.768799. The second layer, using AdaBoost and XGBoost, further improved these results to 0.772166 and 0.771044, respectively. Applying NLP techniques yielded exceptional accuracies of 0.979781 and 0.983893 from the AdaBoost and XGBoost optimizers.

Artificial intelligence and internet of things (IoT) fields have contributed to the flourishment of the industry 4.0 concept. The main benefits include the improvements in terms of device communication, productivity, and efficiency. Nevertheless, there is a downside concerning the security of these systems. The amount of devices and their diversity prove a security risk. Due to this intrusion detection systems are paramount. This paper proposes a novel framework exploiting extreme gradient boosting machine learning model which is optimized by a modified version of the multi-verse optimizer metaheuristic. The UNSW-NB intrusion dataset was used for experimental purposes on which the other cutting-edge techniques were tested and compared. The results provide the proof of improvement as the proposed method outperformed all other overall metaheuristic performances. Furthermore, the units for truthfulness and polarity for the case have been established as a standard evaluation system. True and false positives exist alongside the same negative counterparts. The results provided by these metrics have been visualized and used for further comparison proving the superiority of the performance of the proposed solution.