Search

During last decade, medical imaging has attracted great deal of research interests. Deep learning applications has revolutionized medical image analysis and diseases diagnosis. Convolutional neural networks (CNNs)-a class of deep learning-have been widely used for classification and feature extraction, and they revealed good performance for various imaging applications. However, despite the advances in medicine, malaria remains among the world's deadliest diseases. Only in 2020, malaria recorded 241 million clinical episodes, and 627,000 deaths. The disease is examined visually through a microscope, which depends on the pathologists experience and skills and results may vary in different laboratories. This paper proposes an efficient CNN architecture that could be used in diagnosing of malaria disease. By processing on 27,558 red blood smear cell images with balanced samples of parasitized and unparasitized cells on a publicly available malaria dataset from the National Institute of Health, the proposed model achieves high accuracy rate with 99.8%, 98.2, and 97.7% for training, validation and testing sets. Furthermore, the statistical results approve that the proposed model is outperforming the state-of-the-art models. [ABSTRACT FROM AUTHOR]

Vehicle infrastructure must address the challenges posed by today's advances toward connected and autonomous vehicles. To allow for more flexible architectures, high-bandwidth connections and scalability are needed to connect many sensors and electronic control units (ECUs). At the same time, deterministic and low latency is a critical and significant design requirement to support urgent real-time applications in autonomous vehicles. As a recent solution, the time-sensitive network (TSN) was introduced as Ethernet-based amendments in IEEE 802.1 TSN standards to meet those needs. However, it had hurdle to be overcome before it can be used effectively. This paper discusses the latest studies concerning the automotive Ethernet requirements, including transmission delay studies to improve worst-case end-to-end delay and end-to-end jitter. Also, the paper focuses on the securing Ethernet-based in-vehicle networks (IVNs) by reviewing new encryption and authentication methods and approaches. [ABSTRACT FROM AUTHOR]

As technology scaling increases computer memory's bit-cell density and reduces the voltage of semiconductors, the number of soft errors due to radiation induced single event upsets (SEU) and multi-bit upsets (MBU) also increases. To address this, error-correcting codes (ECC) can be used to detect and correct soft errors, while x-modular-redundancy improves fault tolerance. This paper presents a technique that provides high error-correction performance, high speed, and low complexity. The proposed technique ensures that only correct values get passed to the system output or are processed in spite of the presence of up to three-bit errors. The Hamming code is modified in order to provide a high probability of MBU detection. In addition, the paper describes the new technique and associated analysis scheme for its implementation. The new technique has been simulated, evaluated, and compared to error correction codes with similar decoding complexity to better understand the overheads required, the gained capabilities to protect data against three-bit errors, and to reduce the misdetection probability and false-detection probability of four-bit errors. [ABSTRACT FROM AUTHOR]