Industry 4.0, which was proposed ten years ago to address both the industry’s strengths and faults, has finally been replaced by Industry 5.0. It seeks to put human welfare at the core of manufacturing systems, achieving societal goals beyond employment and growth to firmly provide wealth for the long-term advancement of all of humanity. The purpose of this research is to examine the risks involved in the adoption of Industry 5.0’s architecture. The paper discusses the significance of Industry 5.0 and the advanced technology needed for this industrial revolution, followed by a detailed discussion of Industry 5.0’s human-centric strategy. The comprehensive literature review has resulted in the identification of risks and their mitigation strategies in Industry 5.0 architecture. A taxonomy with respect to different categories of risks has also been proposed. This study classifies Industry 5.0 system assets, identifies platform-independent risks, and develops countermeasures to protect against potential threats, irrespective of the business or domain.

Bacterial classification is a vital step in medical diagnosis. This procedure normally has several stages. An early stage involves inspecting the morphology of the bacterial colonies. Traditionally, a bacterial colony expert inspects the sample to determine the type of bacteria through visual inspection or molecular biology techniques. With advances in image processing, specifically, the use of deep and transfer learning techniques, and the wide availability of cameras, we applied deep and transfer learning techniques to address this task without requiring expert knowledge or sample shipping. We used a convolutional neural network (CNN) to identify different bacterial colonies based on their appearance in images captured by cell phone cameras. In this paper, we collected a dataset that contains images of different bacteria taken by cell phone cameras with various settings. Thus, images of two classes of bacterial colonies were obtained in King Abdulaziz City for Science and Technology. The dataset contains 8,043 images. The experimental results show that our application has high accuracy without requiring expert inspections.

The recent monkeypox outbreak has raised global health concerns. Caused by a virus, it is characterized by symptoms such as skin lesions. Early detection is critical for treatment and controlling its spread. This study uses advanced machine learning and deep learning techniques, including Tab Transformer, Long Short-Term Memory, XGBoost, LightGBM, and a Stacking Classifier, to predict the presence of the virus based on patient symptoms. The performance of these models is evaluated using accuracy, precision, recall, and F1-score metrics. The experiments reveal that the Stacking Classifier significantly outperforms the other models, achieving an accuracy of 87.29 %, precision of 86.12 %, recall of 87.47 %, and an F1 score of 87.89 %. Additionally, applying Conditional Tabular GAN to generate synthetic data helps address data imbalance issues, further improving model robustness. These results highlight the proposed approach's potential for timely, accurate monkeypox detection, aiding in effective disease management and control.

This study explores deep learning techniques that can help diagnose eye conditions, focusing on diabetic retinopathy (DR). By using cutting-edge technology in image processing and artificial intelligence, it aims to better understand and classify various eye issues like microaneurysms, hemorrhages, and others. Despite progress, challenges like poor image quality and noise persist. The paper stresses the need for improved methods to detect small blood vessels while reducing interference. It also addresses the complexity of uneven lighting in extracting blood vessel images from the retina. The main contribution of this study is its thorough examination of existing methods and its detailed investigation into using deep learning for detecting retinal blood vessels. It highlights the effectiveness of different deep learning models and their potential in accurately classifying DR grades. This research underscores the importance of grading methods in analyzing medical images, especially retinal images, to enhance the accuracy of diagnosing eye diseases.

Tawakkalna is an application developed by the Saudi Arabian government to manage the spread of COVID-19 in the country. Even now that the pandemic is under better control, Tawakkalna continues to offer numerous services to its users. People of all age groups, including children and adults, rely on the application on a daily basis. It is important to evaluate the perceived usability of the Tawakkalna (COVID-19 KSA) application. Accordingly, this study aims to evaluate its perceived usability from the perspective of users belonging to all age groups and to identify whether any particular age group is facing difficulties with using it. The study used two existing and well-known questionnaires: The System Usability Scale (SUS) and the Usability Metric for User Experience (UMUX). The study performed descriptive and inferential statistical analysis to present an in-depth understanding and comparison of the survey results. A total of 395 responses were received. The SUS score is 71.1. The UMUX score is 72.0. The results indicate that, overall, the SUS and UMUX scores support each other and grade Tawakkalna’s perceived usability as good. The results also indicate that the mean rank of the UMUX score is higher for the 18-30 age group than for all the other age groups. In addition, children under age 12 and adults greater than age 50 face challenges while using Tawakkalna. Finally, this study presents recommendations to improve the application’s usability.

Speech Emotion Recognition is essential for human-computer interaction, as it enables the automated system to recognize the emotion of the individual from the speech. In order to improve the quantity, diversity, and quality of the speech dataset that deep learning algorithms use to identify the person's emotions, this paper proposes a novel loss function, 'Balanced_Focal_Entropy', that is used to improve the performance of the unbalanced datasets by combining three separate open-source datasets. Two distinct datasets are used in the suggested method: the individual dataset and the hybrid dataset, which combines three distinct open-source datasets. The dataset is enhanced by the addition of noise, pitch shifting, and a combination of these techniques. Then, the four distinct handcrafted feature extraction techniques are employed to extract the features from the speech data, which are then combined to create a single set. These fused features are utilized to train the two deep learning models on the RAVDESS and hybrid datasets with the proposed loss function known as 'Balanced_Focal_Entropy loss'. The RAVDESS dataset achieves 95.23% test accuracy, while the hybrid dataset reaches a maximum of 97.80%. Real-time application of the suggested method can be useful in various domains to accurately identify an individual's emotion.