Abdu Gumaei

Mabrook S. Al-Rakhami, Abdu Gumaei, Sk. Md. Mizanur Rahman et al.

Blockchain technology is among the fastest-growing technologies in the world today. It has been adopted in diverse areas but mostly in financial systems, such as Bitcoin cryptocurrency. Therefore, it is a niche that has attracted interest from researchers from various fields, including computer science. Other areas where Blockchain is being embraced are the Smart Grid and Internet of Things (IoT) technologies, among others. While it is all good and improving many areas of applications, Blockchain still has some shortcomings. For example, it is not designed for high scalability when accommodating normal transactions. On the other hand, a parallel technology that has diverse applications in distributed networks better known as edge computing has emerged. Its main advantage is that it increases the speed of pf processes within those networks. However, like Blockchain, edge computing has its shortcomings. Its security systems and management systems have been found to be wanting. Hence the idea to integrate the two technologies and take advantage of their strengths. A blend of the two would lead to advanced network servers, huge data storage, and heightened security in transactions. However, this integration will best happen when some measures are taken. For example, there is a need to address scalability, resource management satisfactorily, and the security of the systems. To solve the integration problem, a decentralized Blockchain-based model of Edge computing is proposed in this paper.

Samiul Based Shuvo, Shams Nafisa Ali, Soham Irtiza Swapnil et al.

The alarmingly high mortality rate and increasing global prevalence of cardiovascular diseases signify the crucial need for early detection schemes. Phonocardiogram (PCG) signals have been historically applied in this domain owing to its simplicity and cost-effectiveness. In this paper, we propose CardioXNet, a novel lightweight end-to-end CRNN architecture for automatic detection of five classes of cardiac auscultation namely normal, aortic stenosis, mitral stenosis, mitral regurgitation and mitral valve prolapse using raw PCG signal. The process has been automated by the involvement of two learning phases. Three parallel CNN pathways have been implemented in the representation learning phase to learn the coarse and fine-grained features from the PCG and to explore the salient features from variable receptive fields involving 2D-CNN based squeeze-expansion. Thus, in the representation learning phase, the network extracts efficient time-invariant features and converges with great rapidity. In the sequential residual learning phase, with the bidirectional-LSTMs and the skip connection, the network can proficiently extract temporal features without performing any feature extraction on the signal. The obtained results demonstrate that the proposed end-to-end architecture yields outstanding performance in all the evaluation metrics compared to the previous state-of-the-art methods with up to 99.60% accuracy, 99.56% precision, 99.52% recall and 99.68% F1- score on an average while being computationally comparable. This model outperforms the previous works using the same dataset by a considerable margin. The high accuracy metrics on both primary and secondary dataset combined with a significantly low number of parameters and end-to-end prediction approach makes the proposed network suitable for point of care CVD screening in low resource setups using memory constraint mobile devices.