Chonnam National University

Sangmi Moon

Intae Hwang

Chilwoo Lee

Bora Kim

Hyeonsung Kim

Seungkyu Kim

Jihye Lee

Soonho Kwon

Saransh Malik

Myeonghun Chu

Malik Saransh

Provided are a deep learning-based beamforming communication system and method, wherein in an indoor environment using millimeter wave communication, in response to reference signals transmitted from a base station to at least one user terminal, reference signal received power and location information for each user terminal location are received from each user terminal and a fingerprint DB is constructed, and from the constructed fingerprint data, a user model is constructed on the basis of reference signal received power for each user terminal location and a blockage model is constructed on the basis of reference signal received power according to each blockage located between the base station and the user terminal. Location information and data traffic are received from the at least one user terminal, a beam index of the user terminal corresponding to the received data traffic is derived from a deep neural network, and a communication channel between the base station and a user is formed with the derived beam index, whereby reliability and a data transfer rate are improved in an indoor communication environment.

Deep learning-based beamforming communication system and method

A fingerprint-based beam interference cancellation system and a method thereof are proposed. A communication part receives location information and reference signal reception power which is strength of a received signal provided from each user terminal in response to a reference signal, a fingerprint DB construction part constructs a fingerprint database by receiving the reference signal reception power and the location information, a group-based fingerprint DB construction part constructs a group-based fingerprint database by grouping user terminals, aligning the remaining beams, generating group fingerprint data with the aligned beams, and using the generated group fingerprint data, a first beam interference cancellation part generates a beam set for each group from which beam interference within the group is cancelled, and a second beam interference cancellation part removes beams redundant between the groups and cancels intra-group and inter-group beam interference in millimeter wave communication, thereby improving reliability and data transfer rate.

Fingerprint-based beam interference cancellation system and method thereof

Disclosed is an adaptive transmission method for a vehicular communication system, that is, a method of randomly allocating resources in a time domain and a frequency domain to perform vehicular communication in a Long-Term Evolution (LTE)-based vehicle to everything (V2X) system and determining whether to transmit messages according to a transmission probability such that it is possible to improve cumulative distribution functions (CDFs) of packet reception ratios (PRRs) and average PRRs by decreasing interference between vehicles.

Adaptive transmission method and apparatus for improving vehicular communication performance

The present disclosure relates to a machine to machine (M2M) system, method and server using a Social Network Service (SNS). The M2M communication server receives control information of a first M2M apparatus from a second M2M apparatus that receives the control information through an SNS interface, converts the control information into a command that is recognizable by the first M2M apparatus, and transmits the command to the first M2M apparatus such that the second M2M apparatus receives information corresponding to the command. Accordingly, a human, as a user, communicates with an M2M apparatus, easily controls the M2M apparatus, and acquires information by use of a Social Network Service (SNS) interface that is familiar to the human.

Machine to machine system, method and server using social network service

Provided is a method of analyzing performance according to inter-cell interference control based on coordinated multipoint (CoMP) communication in a heterogeneous network (HetNet) to check that performance is enhanced by applying a variety of scheduling and pre-coding based on the CoMP communication in a HetNet environment of a Long Term Evolution-Advanced system to analyze the performance. The method applies a variety of scheduling and pre-coding based on coordinated beamforming scheme of CoMP communication technology, where the scheduling includes coordinated scheduling technique and the precoding includes QR decomposition, Tomlinson-Harashima precoding, polar decomposition, and singular value decomposition techniques, and compares and analyzes performances when there are only macrocells or when there are picocells at the boundaries of the macrocells, thereby checking that the gain is enhanced.

Apparatus and method for analyzing performance according to inter-cell interference control based on coordinated multipoint communication in heterogeneous network

Growing community of inventors

Gwangju, South Korea

Sangmi Moon