Publication detail

Channel Impulse Response Peak Clustering Using Neural Networks

HORKÝ, P. PROKEŠ, A. ZÁVORKA, R. VYCHODIL, J.

Original Title

Channel Impulse Response Peak Clustering Using Neural Networks

Type

conference paper

Language

English

Original Abstract

This paper introduces an approach to process channel sounder data acquired from Channel Impulse Response (CIR) of 60GHz and 80GHz channel sounder systems, through the integration of Long Short-Term Memory (LSTM) Neural Network (NN) and Fully Connected Neural Network (FCNN). Theprimary goal is to enhance and automate cluster detection within peaks from noised CIR data. The study initially compares the performance of LSTM NN and FCNN across different input sequence lengths. Notably, LSTM surpasses FCNN due to its incorporation of memory cells, which prove beneficial for handling longer series. Additionally, the paper investigates the robustness of LSTM NN through various architectural configurations. The findings suggest that robust neural networks tend to closely mimic the input function, whereas smaller neural networks are better at generalizing trends in time series data, which is desirable for anomaly detection, where function peaks are regarded as anomalies. Finally, the selected LSTM NN is compared with traditional signal filters, including Butterworth, Savitzky-Golay, Bessel/Thomson, and median filters. Visual observations indicate that the most effective methods for peak detection within channel impulse response data are either the LSTM NN or median filter, as they yield similar results.

Keywords

LSTM, FCNN, DBSCAN, anomaly detection, clusters, peak detection, channel impulse response

Authors

HORKÝ, P.; PROKEŠ, A.; ZÁVORKA, R.; VYCHODIL, J.

Released

22. 12. 2023

Publisher

Institute of Electrical and Electronics Engineers Inc.

Location

Maroko

ISBN

979-8-3503-2939-1

Book

2023 6th International Conference on Advanced Communication Technologies and Networking (CommNet)

Pages from

1

Pages to

7

Pages count

7

URL

https://commnet-conf.org/6thEditionProceedings/index.html

BibTex

@inproceedings{BUT188305,
  author="Petr {Horký} and Aleš {Prokeš} and Radek {Závorka} and Josef {Vychodil} and Kelner {Jan M.} and Cezary {Ziółkowski} and Aniruddha {Chandra}",
  title="Channel Impulse Response Peak Clustering Using Neural Networks",
  booktitle="2023 6th International Conference on Advanced Communication Technologies and Networking (CommNet)",
  year="2023",
  pages="1--7",
  publisher="Institute of Electrical and Electronics Engineers Inc.",
  address="Maroko",
  doi="10.1109/CommNet60167.2023.10365265",
  isbn="979-8-3503-2939-1",
  url="https://commnet-conf.org/6thEditionProceedings/index.html"
}