Page 233 - Kaleidoscope Academic Conference Proceedings 2020
P. 233
Session 7: AI, machine learning and digital transformation
S7.1 AI-based W-band suspicious object detection system for moving persons using GAN: Solutions,
performance evaluation and standardization activities*
Yutaka Katsuyama, Keping Yu, San Hlaing Myint, Toshio Sato, Zheng Wen and Xin Qi, Waseda
University, Japan
With the intensification of conflicts in different regions, the W-band suspicious object detection
system is an essential security means to prevent terrorist attacks and is widely used in many crucial
places such as airports. Because artificial intelligence can performhighly reliable and accurate
services in the field of image recognition, it is used in suspicious object detection systems to
increase the recognition rate for suspicious objects. However, it is challenging to establish a
complete suspicious object database, and obtaining sufficient millimeter-wave images of
suspicious objects from experiments for AI training is not realistic. To address this issue, this paper
verifies the feasibility to generate a large number of millimeter-wave images for AI training by
generative adversarial networks. Moreover, we also evaluate the factors that affect the AI
recognition rate when the original images used for CNN training are insufficient and how to
increase the service quality of AI-based W-band suspicious object detection systems for moving
persons. In parallel, all the international standardization organizations have been collectively
advancing the novel technologies of AI. We update the reader with information about AI research
and standardization related activities in this paper.
S7.2 An AI-based optimization of handover strategy in non-terrestrial networks*
Chenchen Zhang, Nan Zhang, Wei Cao, Kaibo Tian and Zhen Yang, ZTE Corporation and State
Key Laboratory of Mobile Network and Mobile Multimedia Technology, China
A complicated radio resource management, e.g., handover condition, will be suffered by the user
in non-terrestrial networks due to the impact of high mobility and hierarchical layouts which co-
exist with terrestrial networks or various platforms at different altitudes. It is necessary to optimize
the handover strategy to reduce the signaling overhead and improve the service continuity. In this
paper, a new handover strategy is proposed based on the convolutional neural network. Firstly, the
handover process is modeled as a directed graph. Suppose a user knows its future signal strength,
then it can search for the best handover strategy based on the graph. Secondly, a convolutional
neural network is used to extract the underlying regularity of the best handover strategies of
different users, based on which any user can make near-optimal handover decision according to
its historical signal strength. Numerical simulation shows that the proposed handover strategy can
efficiently reduce the handover number while ensuring the signal strength.
S7.3 BSR: A balanced framework for single image super resolution
Dehui Kong, State Key Laboratory of Mobile Network and Mobile Multimedia Technology and
ZTE Microelectronics Research Institute, China; Fang Zhu, ZTE Corporation, China; Yang Wei,
Song Jianjun, Zhu Tongtong and Bengang Lou, Sanechips, China; Ke Xu, State Key Laboratory
of Mobile Network and Mobile Multimedia Technology and ZTE Microelectronics Research
Institute, China
A complicated radio resource management, e.g., handover condition, will be suffered by the user
in non-terrestrial networks due to the impact of high mobility and hierarchical layouts which co-
exist with terrestrial networks or various platforms at different altitudes. It is necessary to optimize
the handover strategy to reduce the signaling overhead and improve the service continuity. In this
paper, a new handover strategy is proposed based on the convolutional neural network. Firstly, the
handover process is modeled as a directed graph. Suppose a user knows its future signal strength,
then it can search for the best handover strategy based on the graph. Secondly, a convolutional
neural network is used to extract the underlying regularity of the best handover strategies of
different users, based on which any user can make near-optimal handover decision according to
its historical signal strength. Numerical simulation shows that the proposed handover strategy can
efficiently reduce the handover number while ensuring the signal strength.
– 175 –
