ABSTRACT
The extremely high number of services with large bandwidth requirements and the increasingly dynamic traffic patterns of cell sites pose major challenges to optical fronthaul networks, rendering them incapable of coping with the extensive, uneven, and real-time traffic that will be generated in the future. In this paper, we first present the design of an adaptive graph convolutional network with gated recurrent unit (AGCN-GRU) network to learn the temporal and spatial dependencies of traffic patterns of cell sites to provide accurate traffic predictions, in which the AGCN model can capture potential spatial relations according to the similarity of network traffic patterns in different areas. Then, we innovatively consider how to deal with the unpredicted burst traffic and propose an AI-assisted intent-based traffic grooming scheme to realise automatic and intelligent cell sites clustering and traffic grooming. Finally, a software-defined testbed for 5G optical fronthaul network was established, on which the proposed schemes were deployed and evaluated by considering traffic datasets of existing optical networks. The experimental results showed that the proposed scheme can optimize network resource allocation, increase the average efficient resource utilization and reduce the average delay and the rejection ratio.
ABSTRACT
Systolic and diastolic blood pressures (BPs) are important physiological parameters for disease diagnosis. Systolic and diastolic characteristic ratios derived from oscillometric pulse waveform have been widely used to estimate automated non-invasive BPs in oscillometric BP measurement devices. The oscillometric pulse waveform is easily influenced by respiration, which may cause variability to the characteristic ratios and subsequently BP measurement. This study quantitatively investigated how respiration patterns (i.e., normal breathing and deep breathing) affect the systolic and diastolic characteristic ratios. The study was performed with clinical data collected from 39 healthy subjects, and each subject conducted BP measurements during normal and deep breathings. Analytical results showed that the systolic characteristic ratio increased significantly from 0.52 ± 0.13 under normal breathing to 0.58 ± 0.14under deep breathing (p < 0.05), and the diastolic characteristic ratio was not significantly affected from 0.75 ± 0.12 under normal breathing to 0.76 ± 0.13 under deep breathing (p = 0.48). In conclusion, deep breathing significantly affected the systolic characteristic ratio, suggesting that automated oscillometric BP device which is validated under resting condition should be strictly used for measurements under resting condition.
