Connected vehicles are a vital part of smart cities, which connect over a wireless connection and bring mobile computation and communication abilities. As a mediator, fog computing resides between vehicles and the cloud and provides vehicles with processing, storage, and networking power through Vehicular Ad-hoc networks (VANET). VANET is a time-sensitive technology that requires less time to process a request received from a vehicle. Delay and latency are the notorious issues of VANET and fog computing. To deal with such problems, in this work, we developed a priority-based fog computing model for smart urban vehicle transportation that reduces the delay and latency of fog computing. To upgrade the fog computing infrastructure to meet the latency and Quality of Service (QoS) requirements, 5G localized Multi-Access Edge Computing (MEC) servers have also been used, which resulted tremendously in reducing the delay and the latency. We decreased the data latency by 20% compared to the experiment carried using only cloud computing architecture. We also reduced the processing delay by 35% compared with the utilization of cloud computing architecture.

No abstract

No abstract

With the rapid development of deep learning techniques, new innovative license plate recognition systems have gained considerable attention from researchers all over the world. These systems have numerous applications, such as law enforcement, parking lot management, toll terminals, traffic regulation, etc. At present, most of these systems rely heavily on high-end computing resources. This paper proposes a novel memory and time-efficient automatic license plate recognition (ALPR) system developed using YOLOv5. This approach is ideal for IoT devices that usually have less memory and processing power. Our approach incorporates two stages, i.e., using a custom transfer learned model for license plate detection and an LSTM-based OCR engine for recognition. The dataset that we used for this research was our dataset consisting of images from the Google open images dataset and the Indian License plate dataset. Along with training YOLOv5 models, we also trained YOLOv4 models on the same dataset to illustrate the size and performance-wise comparison. Our proposed ALPR system results in a 14 megabytes model with a mean average precision of 87.2% and 4.8 ms testing time on still images using Nvidia T4 GPU. The complete system with detection and recognition on the other hand takes about 85 milliseconds.

This chapter discusses a deep learning and IoE (Internet of Everything) based analytical model for disease detection, prediction and correct treatment for the patient would be proposed. In the proposed model, all the stakeholders, namely doctors, patients, medical staff within a clinic, hospital or a medical institute, would be embedded with micro-sensors. The sensors would in turn sense and capture the information gathered from these sources and the surrounding environment and then send it to a single repository, a base or a server, where it would be stored for further processing. These sensors produce massive amounts of data, which needs to be encrypted as well. Then, in order to improve the effectiveness and accuracy of prediction from the data received from these sensors, deep learning methods are used. Further, the advantages of the proposed model would be explored. To conclude, the limitations, opportunities and future applications of deep learning techniques would be discussed in this chapter.

No abstract

(readers, tags, software, and security programs).

No abstract