基于LSTM的邊境頻譜占用度預測

打開文本圖片集
摘要:通過長短記憶神經網絡對邊境頻譜占用度數(shù)據(jù)進行學習,建立了基于邊境頻譜占用度數(shù)據(jù)特征的預測模型,分析了影響預測準確度的主要因素并得出結論。實驗結果表明,文章中提出的預測模型具有較高的準確性,是一種有效的邊境頻譜占用度預測方法。
關鍵詞:深度學習;LSTM;頻譜占用度預測
doi:10.3969/J.ISSN.1672-7274.2022.07.008
中圖分類號:TN 98 文獻標示碼:A 文章編碼:1672-7274(2022)07-00-03
Spectrum Occupancy Prediction Based on LSTM
LU Weidong, LUO Shiwei, LIU Yizhuo
(State Radio Monitoring Center Harbin Monitoring Station, Harbin 150010, China)
Abstract: Based on the long and short memory neural network, a prediction model based on the characteristics of border spectrum occupancy data was established, and the main factors affecting the accuracy of prediction were analyzed. The experimental results show that the proposed prediction model has high accuracy and is an effective method for predicting border spectrum occupancy.
Key words: deep learning; LSTM; spectrum occupancy prediction
0 引言
頻譜占用度是用來描述無線電頻譜資源利用率的重要指標,其也可以反映一個地區(qū)的頻譜利用率變化趨勢,邊境地區(qū)的無線電監(jiān)測的重要任務之一就是獲取準確的頻譜占用度,為上級無線電主管部門制定頻率使用規(guī)劃和國際臺站申報計劃提供重要依據(jù)。(剩余1421字)