5G and Beyond Technology-enabled e-Health (5GB e-Health)

Session WS2-1

Session 1

Conference
2:00 PM — 3:30 PM CST
Local
Aug 9 Sun, 2:00 AM — 3:30 AM EDT

European 5G Healthcare Vertical Trials

Haesik Kim ([email protected]), the VTT Technical Research Centre of Finland

0
This talk does not have an abstract.

A Network Slicing Strategy for Telemedicine based on Classification

Yajing Liu and Luhan Wang (Beijing University of Posts and Telecommunications, China); Xiang Ming Wen (Beijing University of posts and telecommunications, China); Zhaoming Lu and Luning Liu (BUPT, China)

0
Telemedicine is the inevitable trend of medical development. Diverse categories of telemedicine put forward different demands to network. As an important enabler of 5G, network slicing can meet different service requirements in telemedicine scenario by slicing multiple isolated virtual networks on the same physical infrastructure. How to ensure telemedicine services through network slicing with limited resources has always been a problem to be solved. In this paper, we consider hierarchical telemedicine slicing to serve customized services. What's more, a telemedicine services classification model based on Radial Basis Function (RBF) neural network is proposed to match 5G remote health services with appropriate slice. Then we propose a hierarchical resource allocation strategy based on genetic algorithm to adjust inter-slice and intra-slice resources. Finally, simulation results show the effectiveness of the proposed scheme.

Session Chair

Di Zhang

Session WS2-2

Session 2

Conference
4:00 PM — 5:30 PM CST
Local
Aug 9 Sun, 4:00 AM — 5:30 AM EDT

Neural network promotes the transmission quality of remote health based on 5G technology

Bohang Li (Zhengzhou University, China); Gangcan Sun (Zhengzhou University, China); Wanming Hao (Zhengzhou University, China)

0
In this paper, to improve the wireless channel transmission quality in remote health using 5G, Bi-LSTM (Bi-directional Long Short Term Memory) neural network based channel estimation method is proposed to solve the problem of limited performance of traditional channel estimation methods in complex multipath channel environment. The wireless channel in this paper is processed in an end-to-end way, and compared with the traditional method which estimates CSI before recovering the signal, we use deep learning tools to directly obtain the transmitted signal and hiding the CSI in the process. In order to solve the problem of channel distortion, the autoregressive process is used in the model of wireless communication channel. The WINNER II channel parameters are used to generate training data. Besides, we use the iterative training process of neural network to obtain the optimal solution of the channel autoregressive coefficient. From the simulation results, in the complex multipath channel environment, compared with the traditional channel estimation method (LS and MMSE) and the channel estimation method using DNN (Deep Neural Networks), the performance of BER in our network is better. And compared with the performance of NMSE with increasing number of pilots, our network has the best performance on 5G wireless signal transmission, which can consider to be used in remote health.

Downlink User Matching and Power Allocation for Multicarrier NOMA-based Remote Health System

Gangcan Sun (Zhengzhou University, China); Yapei Lv and Zhengyu Zhu (Zhengzhou University, China)

0
Remote health system greatly relies on the high-speed transmission to realize timely delivery and feedback of user information. In order to enable people in remote areas to be more deeply integrated into the Internet of health and obtain high-quality healthcare, the resource allocation for maximizing throughput of remote health system based on the multi-carrier non-orthogonal multiple access (NOMA) downlink transmission scenario is studied in this paper. We first propose a two-step matching algorithm to quickly achieve stable matching between all system users and subcarriers. We then give the closed-form expressions of optimal power allocation between multiplexing users by constraining the power budgets and minimum service rate (MSR) thresholds. On this basis, the excess power is allocated across subcarriers in a water-filling form. Simulation results show that the proposed scheme can significantly enhance the system throughput while guaranteeing the quality of health service of all access users.

Cost Minimization for Remote Health Monitoring Under Delay and Reliability Constraints

Jingheng Zheng (Beijing University of Posts and Telecommunications, China); Hui Tian (Beijng university of posts and telecommunications, China); Wanli Ni (Beijng University of Posts and Telecommunications, China); Yong Sun (State Grid Shandong Electric Power Research Institute, China)

1
Recently, the pandemic of Coronavirus disease 2019 (COVID-19) highlights the great potential of remote health for resisting infectious diseases. The remote healthcare methodologies have achieved significant development based on reliable and low-latency transmissions of 5G. In remote health monitoring, the Internet of Things (IoT)-based physical monitoring devices need to transmit collected physical data in a real time and highly reliable manner to ensure accurate monitoring of patients. However, due to the unreliability of wireless link and the latency of data queue, it is a challenging issue to achieve high reliability communication and low delay transmission at the same time. Meanwhile, the available bandwidth is limited and the cost of renting spectrum is not negligible. Thus, it is essential for the devices to reduce communication costs while ensuring the efficient data transmission. Toward this end, our goal is to minimize the total costs of leasing bandwidth by jointly optimizing the access link and backhaul transmission, subject to the delay and reliability constraints. Considering the requirements of access link and queue together, a cost minimization problem is formulated, which is non-linear and non-convex and is hard to solve straightforwardly. Through problem equivalent transforming, a gradient descent-based algorithm is proposed to find a suboptimal solution. Simulation results validate the performance through cost, reliability, delay and those under harsh conditions.

A Low Complexity Algorithm for Time-Frequency Joint Estimation of CAF Based on Numerical Fitting

Zhengyu Zhang, Yongqing Zou, Renfei Zhang and Xin Wang (The 38th Research Institute of China Electronics Technology Group Corporation, China)

0
In order to reduce the complexity of cross ambiguity function (CAF), this paper proposes a low-complexity time-frequency joint estimation algorithm based on numerical fitting for CAF. The algorithm makes full use of the property that CAF is symmetrical in the frequency domain. Firstly, the CAF is used to perform time-frequency joint rough estimation. In order to meet the frequency estimation accuracy requirement, the radial basis function (RBF) method is used to estimate the frequency difference near the frequency difference estimation after delay compensation. On the one hand, do time-frequency joint rough estimation can greatly reduce the complexity of the search based on CAF, then sampling the CAF and using RBF for numerical fitting near the result of rough estimation of frequency, and obtaining the frequency difference through can also reduce the complexity of the search; on the other hand, compared to existing algorithms, the methods based on numerical fitting can reduce the priori information needed for estimation, avoid long-term observations and complex pre-level operations. The simulation results show that compared with the method which searches the peak of CAF, the proposed algorithm can greatly reduce the complexity while satisfying the accuracy requirements of time-frequency joint estimation.

Session Chair

Di Zhang

Made with in Toronto · Privacy Policy · © 2020 Duetone Corp.