Machine Learning-Based Channel State Estimators for 5G Wireless Communication Systems

For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pairs through offline training to estimate the channel state information.Also,it utilizes pilots to offer more helpful information about the communication channel.The proposedCNN-CSE performance is compared with previously published results for Bidirectional/long short-term memory(BiLSTM/LSTM)NNs-based CSEs.The CNN-CSE achieves outstanding performance using sufficient pilots only and loses its functionality at limited pilots compared with BiLSTM and LSTM-based estimators.Using three different loss function-based classification layers and the Adam optimization algorithm,a comparative study was conducted to assess the performance of the presented DNNs-based CSEs.The BiLSTM-CSE outperforms LSTM,CNN,conventional least squares(LS),and minimum mean square error(MMSE)CSEs.In addition,the computational and learning time complexities for DNN-CSEs are provided.These estimators are promising for 5G and future communication systems because they can analyze large amounts of data,discover statistical dependencies,learn correlations between features,and generalize the gotten knowledge.

Design and Implementation of Initial Cell Search in 5G NR Systems

The initial cell search plays an important role during the process of downlink synchronization establishment between the User Equipment(UE) and the base station. In particular, the uncertainty of the synchronization signals on the frequency domain and the flexibility of frame structure configuration have brought great challenges to the initial cell search for the fifth-generation(5G) new radio(NR). To solve this problem, firstly, we analyze the physical layer frame structure of 5G NR systems. Then, by focusing on the knowledge of synchronization signals, the 5G NR cell search process is designed, and the primary synchronization signal(PSS) timing synchronization algorithm is proposed, including a 5G-based coarse synchronization algorithm and conjugate symmetry-based fine synchronization algorithm. Finally, the performance of the proposed cell search algorithm in 5G NR systems is verified through the combination of Digital Signal Processing(DSP) and personal computer(PC). And the MATLAB simulation proves that the proposed algorithm has better performance than the conventional cross-correlation algorithm when a certain frequency offset exists.

Challenges for beyond 5G:ultra-densification of radio access network

Ultra-densification of radio access network(RAN)is a key to efficiently support the exponentially growing mobile data traffic in 5 G era.Furthermore,extremely high frequency band like mm Wave band was utilized to solve the bandwidth shortage problem.However,untra-dense reusing the same radio resource produced severe interference.And the mm Wave link was very harsh due to frequent blockage by obstacles.Therefore a new RAN architecture needed to be introduced to realize ultra-reliable communications in such a severe radio propagation environment.An architecture of distributed MIMO based RAN was presented.Then,enhanced interference coordination(e IC)was described.Finally,the effectiveness of distributed MIMO based RAN with e IC by computer simulation was showed.

Electron Spin Resonance(ESR)Spectroscopy of the Transition-metal Complexes and Clusters I.Systematic Investigations of Real-and Complex-Orbital Methods for Calculating the d-Orbital Energies of a Low-spin(S=1/2)nd^5(t_2~5,~2T_2)(n=3

On the basis of the first paper’s theoretical derivations and concrete instance calculations of the energies of the d orbitals for a low spin ( S =1/2) nd 5(t 2 5, 2T 2)(n =3, 4, 5) system, the major results reported in this paper contain the following two respects: explicit relationships between the coefficients of the real and complex Kramers doublets have been derived by using two types of the expressions of the principal components of the g tensors in real and complex orbital representations obtained in the first paper; the use of these relationships of the real and complex orbital coefficients has carried out a series of mathematical demonstrations on the agreement of the real and complex orbital methods .

The Asymmetric Laplace Law for distribution of aluminum contact resistance in spot welding

This paper investigates the distribution of contact resistance of the aluminum alloy in the squeeze stage. A new method of measuring path＇ s resistance is proposed firstly. Contact resistances are calculated accurately by the systems of 5 linear equations and solutions show that three contact resistances are different. The probability density functions of contact resistance in workpiece/workpiece（ W/W） and upper electrode/workpiece（ E/W） show that the curve shape has steeper peak and heavier tail than that of the normal distribution. Non-parameter hypothesis test is performed and the result shows that R2 , R4 reject the normal distribution using chi-square and kolmogoroo statistic D method. Therefore, the Asymmetric Laplace distribution is fitted to empirical distributions and is applied to quantify the influence of random contact resistance. The result illustrates that AL distribution is very close to contact resistance of W/W and upper E/W and normal distribution has some deviation. The paper is helpful to research the initial nugget conditions, weldability and the transient multi-coupling field.

Special issue on 5G wireless communication systems and technologies

The explosive growth of data traffic due to ubiquitous smart devices has accelerated the evolution of mobile communication from 4G to 5G. To achieve an extremely high performance, 5G mobile communication system is facing challenges in the design of new network architectures, new radio access techniques, and new transmission waveforms. Motivated by this observation, FITEE organizes this special issue on 5G Wireless Communication Systems and Technologies, to advance the studies of this field.

Energy-efficiency based downlink multi-user hybrid beamforming for millimeter wave massive MIMO system

The fifth generation mobile communication（5G） systems can provide Gbit/s data rates from massive multiple-input multiple-output（MIMO） combined with the emerging use of millimeter wavelengths in small heterogeneous cells. This paper develops an energy-efficiency based multi-user hybrid beamforming for downlink millimeter wave（mm Wave） massive MIMO systems. To make better use of directivity gains of the analog beamforming and flexible baseband processing of the digital beamforming, this paper proposes the analog beamforming to select the optimal beam which can maximize the power of the objective user and minimize the interference to all other users. In addition, the digital beamforming maximizes the energy efficiency of the objective user with zero-gradient-based approach. Simulation results show the proposed algorithm provide better bit error rate（BER） performance compared with the traditional hybrid beamforming and obviously improved the sum rate with the increase in the number of users. It is proved that multi-user MIMO（MU-MIMO） can be a perfect candidate for mm Wave massive MIMO communication system. Furthermore, the analog beamforming can mitigate the inter-user interference more effectively with the selection of the optimal beam and the digital beamforming can greatly improve the system performance through flexible baseband processing.

Toll-like receptor 9 is correlated to disease activity in Chinese systemic lupus erythematosus population

Methods mRNA level of TLR9 and interferon （IFN） regulatory factor 5 （IRF5） in peripheral blood mononuclear cells （PBMCs） were determined by real-time polymerase chain reaction （PCR）. IFN-a expression was measured in the serum of the SLE patients by enzyme-linked immunosorbent assay （ELISA）. Results TLR9 expression was significantly higher in SLE patients than that in health controls （P=0.011）. SLE patients with positive anti-dsDNA antibody had significantly higher expression of TLR9 than that with negative anti-dsDNA antibody （P=0.001）. TLR9 expression was positively correlated with fever （P=0.017）, alopecia （P=0.046）, safety of estrogens in lupus erythematosus national assessment SLE disease activity index （SELENA-SLEDAI） score （rs=0.385, P=0.003）, and the level of IRF5 （rs=0.35, P=0.027） and IFN-a （rs=0.627, P=0.001） in SLE patients. Conclusion TLR9 is associated with SLE disease activity and might be involved in the IFN-a pathway of SLE.

Call for Papers

URL:http://www.infotech.monash.edu.au/about/news/conferences/icsssm08/ Contact email:vincent.lee@infotech.monash.edu.au Conference Theme and Scope The last decade has seen rapid growth of service-based economic activities in many advanced developed economies such as the USA,European and developed Asian countries as well as emerging