Chest X-ray imaging is a relatively cheap and accessible diagnostic tool that can assist in the diagnosis of various conditions, including pneumonia, tuberculosis, COVID-19, and others. However, the requirement for expert radiologists to view and interpret chest X-ray images can be a bottleneck, especially in remote and deprived areas. Recent advances in machine learning have made possible the automated diagnosis of chest X-ray scans. In this work, we examine the use of a novel Transformer-based deep learning model for the task of chest X-ray image classification. We first examine the performance of the Vision Transformer (ViT) state-of-the-art image classification machine learning model for the task of chest X-ray image classification, and then propose and evaluate the Input Enhanced Vision Transformer (IEViT), a novel enhanced Vision Transformer model that can achieve improved performance on chest X-ray images associated with various pathologies. Experiments on four chest X-ray image data sets containing various pathologies (tuberculosis, pneumonia, COVID-19) demonstrated that the proposed IEViT model outperformed ViT for all the data sets and variants examined, achieving an F1-score between 96.39% and 100%, and an improvement over ViT of up to +5.82% in terms of F1-score across the four examined data sets. IEViT's maximum sensitivity (recall) ranged between 93.50% and 100% across the four data sets, with an improvement over ViT of up to +3%, whereas IEViT's maximum precision ranged between 97.96% and 100% across the four data sets, with an improvement over ViT of up to +6.41%. Results showed that the proposed IEViT model outperformed all ViT's variants for all the examined chest X-ray image data sets, demonstrating its superiority and generalisation ability. Given the relatively low cost and the widespread accessibility of chest X-ray imaging, the use of the proposed IEViT model can potentially offer a powerful, but relatively cheap and accessible method for assisting diagnosis using chest X-ray images.

The inability to see makes moving around very difficult for visually impaired persons. Due to their limited movement, they also struggle to protect themselves against moving and non-moving objects. Given the substantial rise in the population of those with vision impairments in recent years, there has been an increasing amount of research devoted to the development of assistive technologies. This review paper highlights the state-of-the-art assistive technology, tools, and systems for improving the daily lives of visually impaired people. Multi-modal mobility assistance solutions are also evaluated for both indoor and outdoor environments. Lastly, an analysis of several approaches is also provided, along with recommendations for the future.

It can be difficult for a visually impaired person to move on their own and use a typical white cane to identify items such as people, animals, crosswalks, pavements, and uneven terrain. A smart assistive navigation system is proposed in this research that combines voice-over with object detection. The system aims to promote the independence of visually impaired navigation by offering guidance with auditory feedback and tactile input to the visually impaired user upon object recognition. The created mobile application uses voice and audio only to provide navigational guidance to users. The object detection model used is YOLOV8, implemented on a Raspberry Pi equipped with a camera, speaker, ultrasonic sensor, and moisture sensor. The average accuracy score of nine tested obstacles using YOLOV8 was 91.70%. In addition to identifying objects, the built prototype allows the user to move between locations while giving them access to environmental data such as item distance, orientation, and surface wetness. The goal of this research is to enable people who are visually impaired to move about in both indoor and outdoor spaces securely and freely.

The global COVID-19 pandemic that started in 2019 and created major disruptions around the world demonstrated the imperative need for quick, inexpensive, accessible and reliable diagnostic methods that would allow the detection of infected individuals with minimal resources. Radiography, and more specifically, chest radiography, is a relatively inexpensive medical imaging modality that can potentially offer a solution for the diagnosis of COVID-19 cases. In this work, we examined eleven deep convolutional neural network architectures for the task of classifying chest X-ray images as belonging to healthy individuals, individuals with COVID-19 or individuals with viral pneumonia. All the examined networks are established architectures that have been proven to be efficient in image classification tasks, and we evaluated three different adjustments to modify the architectures for the task at hand by expanding them with additional layers. The proposed approaches were evaluated for all the examined architectures on a dataset with real chest X-ray images, reaching the highest classification accuracy of 98.04% and the highest F1-score of 98.22% for the best-performing setting.