Traffic Sign Recognition Using Multi-Task Deep Learning for Self-Driving Vehicles.

Over the coming years, the advancement of driverless transport systems for people and goods that are designed to be used on fixed routes will revolutionize the transportation system. Therefore, for a safe transportation system, detecting and recognizing traffic signals based on computer vision has become increasingly important. Deep learning approaches, particularly convolutional neural networks, have shown exceptional performance in various computer vision applications. The goal of this research is to precisely detect and recognize traffic signs that are present on the streets using computer vision and deep learning techniques. Previous work has focused on symbol-based traffic signals, where popular single-task learning models have been trained and tested. Therefore, several comparisons have been conducted to select accurate single-task learning models. For further improvement, these models are employed in a multi-task learning approach. Indeed, multi-task learning algorithms are built by sharing the convolutional layer parameters between the different tasks. Hence, for the multi-task learning approach, different experiments have been carried out using pre-trained architectures like, for instance, InceptionResNetV2 and DenseNet201. A range of traffic signs and traffic lights are employed to validate the designed model. An accuracy of 99.07% is achieved when the entire network has been trained. To further enhance the accuracy of the model for traffic signs obtained from the street, a region of interest module is added to the multi-task learning module to accurately extract the traffic signs available in the image. To check the effectiveness of the adopted methodology, the designed model has been successfully tested in real-time on a few Riyadh highways.

Vision-Language Model for Visual Question Answering in Medical Imagery.

In the clinical and healthcare domains, medical images play a critical role. A mature medical visual question answering system (VQA) can improve diagnosis by answering clinical questions presented with a medical image. Despite its enormous potential in the healthcare industry and services, this technology is still in its infancy and is far from practical use. This paper introduces an approach based on a transformer encoder-decoder architecture. Specifically, we extract image features using the vision transformer (ViT) model, and we embed the question using a textual encoder transformer. Then, we concatenate the resulting visual and textual representations and feed them into a multi-modal decoder for generating the answer in an autoregressive way. In the experiments, we validate the proposed model on two VQA datasets for radiology images termed VQA-RAD and PathVQA. The model shows promising results compared to existing solutions. It yields closed and open accuracies of 84.99% and 72.97%, respectively, for VQA-RAD, and 83.86% and 62.37%, respectively, for PathVQA. Other metrics such as the BLUE score showing the alignment between the predicted and true answer sentences are also reported.

Contrasting EfficientNet, ViT, and gMLP for COVID-19 Detection in Ultrasound Imagery.

A timely diagnosis of coronavirus is critical in order to control the spread of the virus. To aid in this, we propose in this paper a deep learning-based approach for detecting coronavirus patients using ultrasound imagery. We propose to exploit the transfer learning of a EfficientNet model pre-trained on the ImageNet dataset for the classification of ultrasound images of suspected patients. In particular, we contrast the results of EfficentNet-B2 with the results of ViT and gMLP. Then, we show the results of the three models by learning from scratch, i.e., without transfer learning. We view the detection problem from a multiclass classification perspective by classifying images as COVID-19, pneumonia, and normal. In the experiments, we evaluated the models on a publically available ultrasound dataset. This dataset consists of 261 recordings (202 videos + 59 images) belonging to 216 distinct patients. The best results were obtained using EfficientNet-B2 with transfer learning. In particular, we obtained precision, recall, and F1 scores of 95.84%, 99.88%, and 24 97.41%, respectively, for detecting the COVID-19 class. EfficientNet-B2 with transfer learning presented an overall accuracy of 96.79%, outperforming gMLP and ViT, which achieved accuracies of 93.03% and 92.82%, respectively.

Leveraging Blockchain Technology for Secure Energy Trading and Least-Cost Evaluation of Decentralized Contributions to Electrification in Sub-Saharan Africa.

The International Energy Agency has projected that the total energy demand for electricity in sub-Saharan Africa (SSA) is expected to rise by an average of 4% per year up to 2040. It implies that ~620 million people are living without electricity in SSA. Going with the 2030 vision of the United Nations that electricity should be accessible to all, it is important that new technology and methods are provided. In comparison to other nations worldwide, smart grid (SG) is an emerging technology in SSA. SG is an information technology-enhanced power grid, which provides a two-way communication network between energy producers and customers. Also, it includes renewable energy, smart meters, and smart devices that help to manage energy demands and reduce energy generation costs. However, SG is facing inherent difficulties, such as energy theft, lack of trust, security, and privacy issues. Therefore, this paper proposes a blockchain-based decentralized energy system (BDES) to accelerate rural and urban electrification by improving service delivery while minimizing the cost of generation and addressing historical antipathy and cybersecurity risk within SSA. Additionally, energy insufficiency and fixed pricing schemes may raise concerns in SG, such as the imbalance of order. The paper also introduces a blockchain-based energy trading system, which includes price negotiation and incentive mechanisms to address the imbalance of order. Moreover, existing models for energy planning do not consider the effect of fill rate (FR) and service level (SL). A blockchain levelized cost of energy (BLCOE) is proposed as the least-cost solution that measures the impact of energy reliability on generation cost using FR and SL. Simulation results are presented to show the performance of the proposed model and the least-cost option varies with relative energy generation cost of centralized, decentralized and BDES infrastructure. Case studies of Burkina Faso, Cote d'Ivoire, Gambia, Liberia, Mali, and Senegal illustrate situations that are more suitable for BDES. For other SSA countries, BDES can cost-effectively service a large population and regions. Additionally, BLCOE reduces energy costs by approximately 95% for battery and 75% for the solar modules. The future BLCOE varies across SSA on an average of about 0.049 $/kWh as compared to 0.15 $/kWh of an existing system in the literature.