This article emphasises the urgent need for appropriate communication tools for communities of people who are deaf or hard-of-hearing, with a specific emphasis on Arabic Sign Language (ArSL). In this study, we use long short-term memory (LSTM) models in conjunction with MediaPipe to reduce the barriers to effective communication and social integration for deaf communities. The model design incorporates LSTM units and an attention mechanism to handle the input sequences of extracted keypoints from recorded gestures. The attention layer selectively directs its focus toward relevant segments of the input sequence, whereas the LSTM layer handles temporal relationships and encodes the sequential data. A comprehensive dataset comprised of fifty frequently used words and numbers in ArSL was collected for developing the recognition model. This dataset comprises many instances of gestures recorded by five volunteers. The results of the experiment support the effectiveness of the proposed approach, as the model achieved accuracies of more than 85% (individual volunteers) and 83% (combined data). The high level of precision emphasises the potential of artificial intelligence-powered translation software to improve effective communication for people with hearing impairments and to enable them to interact with the larger community more easily.

Coronavirus disease (COVID-19), which is caused by SARS-CoV-2, has been announced as a global pandemic by the World Health Organization (WHO), which results in the collapsing of the healthcare systems in several countries around the globe. Machine learning (ML) methods are one of the most utilized approaches in artificial intelligence (AI) to classify COVID-19 images. However, there are many machine-learning methods used to classify COVID-19. The question is: which machine learning method is best over multi-criteria evaluation? Therefore, this research presents benchmarking of COVID-19 machine learning methods, which is recognized as a multi-criteria decision-making (MCDM) problem. In the recent century, the trend of developing different MCDM approaches has been raised based on different perspectives; however, the latest one, namely, the fuzzy decision by opinion score method that was produced in 2020, has efficiently been able to solve some existing issues that other methods could not manage to solve. because of the multiple criteria decision-making problem and because some criteria have a conflict problem. The methodology of this research was divided into two main stages. The first stage related to identifying the decision matrix used eight different ML methods on chest X-ray (CXR) images and extracted a new decision matrix so as to assess the ML methods. The second stage related to FDOSM was utilized to solve the multiple criteria decision-making problems. The results of this research are as follows: (1) The individual benchmarking results of three decision makers are nearly identical; however, among all the used ML methods, neural networks (NN) achieved the best results. (2) The results of the benchmarking group are comparable, and the neural network machine learning method is the best among the used methods. (3) The final rank is more logical and closest to the decision-makers' opinion. (4) Significant differences among groups' scores are shown by our validation results, which indicate the authenticity of our results. Finally, this research presents many benefits, especially for hospitals and medical clinics, with a view to speeding up the diagnosis of patients suffering from COVID-19 using the best machine learning method.