Search

The phenomenal success and popularity of peer-to-peer (p2p) streaming over the last decade took many providers, researchers, as well as the mass, by surprise. It would become the dominant type of traffic over the Internet in the very near future. The released Windows Vista contains its own P2P networking system. Though P2P streaming has become one of the most attractive network applications, it is still awaiting some technological breakthroughs. P2P streaming faces very different challenges from other P2P applications, such as file download. In live P2P streaming, the stringent real-time performance requirement in terms of bandwidth and latency is one of the challenges it faces. In addition, frequent joining and leaving of the autonomous end-hosts have more significant impact on the system performance. So the churn problem and reconstruction due to uncertainty are key challenges of P2P streaming. A number of solutions were proposed which did not take all the factors into account. This paper presents IAM (IP Address Matching), a novel protocol for P2P live streaming system. For overlay structure, neighbor selection algorithm-FAMM (Forward Address Maximum Matching), which allows the peer choose the close peers as neighbors, is proposed. In this mechanism peer selects neighbors by matching IP address in regular expression. IP address is assigned by area basically, so the closer the peers are, the more the same bits of IP address they have. Peer chooses the first m (m > 0) peers whose IP address has same bits with it as the neighbors. Meanwhile, the latency is generally low. FAMM just likes the DHT routing. As managing peer failures and proper recovery are of critical importance for a robust P2P streaming system, a new peer exception mechanism is also proposed which is the other central issue of the IAM. According to the different error information which the peer receives, it detects the departure or failure of the neighbor intelligently and recovers from an unstable state promptly. To evaluate the performance of the IAM, we have conducted extensive simulations and real-network experiment. The results indicate that IAM shortens the latency and is robust to the dynamic peers. It achieves superior comprehensive performance over Random scheme. It is proved effective in the real-network environment, and the latency of recovery is shortened significantly which is only 25% of that with the usual mechanism, as well. [ABSTRACT FROM AUTHOR]

In recent years, deep learning (DNN) based methods have made leapfrogging level breakthroughs in detecting cardiac arrhythmias as the cost effectiveness of arithmetic power, and data size has broken through the tipping point. However, the inability of these methods to provide a basis for modeling decisions limits clinicians' confidence on such methods. In this paper, a Gate Recurrent Unit (GRU) and decision tree fusion model, referred to as (T-GRU), was designed to explore the problem of arrhythmia recognition and to improve the credibility of deep learning methods. The fusion model multipathway processing time-frequency domain featured the introduction of decision tree probability analysis of frequency domain features, the regularization of GRU model parameters and weight control to improve the decision tree model output weights. The MIT-BIH arrhythmia database was used for validation. Results showed that the low-frequency band features dominated the model prediction. The fusion model had an accuracy of 98.31%, sensitivity of 96.85%, specificity of 98.81%, and precision of 96.73%, indicating its high reliability and clinical significance. [ABSTRACT FROM AUTHOR]

Image enhancement technology is often used to improve the quality of medical images and helps doctors or expert systems identify and diagnose diseases. This paper aimed at the characteristics of magnetic resonance imaging (MRI) with complex and difficult-to-enhance details and to propose a nonsubsampled contourlet transform- (NSCT-) based enhancement algorithm called MIE-NSCT. NSCT was used for MRI sub-band decomposition. For high-pass sub-bands, four fuzzy rules were proposed to enhance multiscale and multidirectional edge contour details from adjacent eight directions, whilst for low-pass sub-bands, a new adaptive histogram enhancement algorithm was proposed. The problem of noise amplification and loss of details during the enhancement process was solved. The algorithm was verified on the public dataset BraTS2017 and compared with other advanced methods. Experimental results showed that MIE-NSCT had obvious advantages in improving the quality of medical images, and high-quality medical images showed enhanced performance in grading tumour. MIE-NSCT is suitable for integration into an interactive expert system to provide support for the visualization of disease diagnosis. [ABSTRACT FROM AUTHOR]