Received Path Power Prediction for Millimeter-wave Using LSTM under Indoor Environments
- Resource Type
- Conference
- Authors
- Yamazaki, Takato; Ohno, Kohei
- Source
- 2022 25th International Symposium on Wireless Personal Multimedia Communications (WPMC) Wireless Personal Multimedia Communications (WPMC), 2022 25th International Symposium on. :211-215 Oct, 2022
- Subject
- Aerospace
Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Geoscience
Nuclear Engineering
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Legged locomotion
Wireless communication
Millimeter wave technology
Transfer functions
Machine learning
Frequency conversion
Indoor environment
deep learning
received power prediction
neural etwork
illimeter-wave
- Language
- ISSN
- 1882-5621
This paper discusses the received path power prediction technique by machine learning techniques. The technique is assumed that a user moves simply like walking straight, then the received power is predicted after the current position. In this paper, the LSTM (Long Short Term Memory) is used for the prediction. The LSTM is suited for prediction using the time sequence data. To increase the data used for learning, the technique that the wider channel transfer function is divided into narrower functions, and the power of the arrival path is obtained from the narrower channels is adopted for the LSTM network. The errors between the received path power obtained from the experiment and predicted data are evaluated to show the effectiveness of the proposed techniques.