Scholarlink

Anomalies experienced in wireless communication systems have been a thing of serious concern. These anomalies present themselves as signal distorters in the forms of impairment, attenuation, interference, and many more. As such, this research adopted the use of the machine learning (ML) algorithm, a sub-field of artificial intelligence (AI) to explore and correct some anomalies experienced in the physical layer of wireless communications systems. These anomalies are the discrepancies observed between the transmitted signal waveform and the received signal waveform, but in this research work, the focus is on interference anomalies that degrade the quality and performance of the wireless communication systems. This activity would be performed in the Channel Estimation Region (CER) of a Feedback Filtered Orthogonal Frequency Division Multiplexing (FF-OFDM) induced waveform because of its scalability in driving variable Tone Spaces (TSs) and in extension varying air interfaces. Results obtained showed an interference anomalies accuracy detection of 98%, specificity of 0.9545%, and sensitivity of 1.000%. This high efficiency is obtained by the hybridization of the Naïve Bayes—Support Vector Machine (NB-SVM) method of Supervised Learning (SL) algorithms of ML. These results simply suggest that the deployment of AI in wireless technology as proposed by Third Generation Partnership Project (3GPP) to activate Fifth Generation (5G) New Radio (NR) Frequency Two-Advanced (FR2-A) waveform has brought a limelight in interference anomalies detection and mitigation, suitable for deployment in the modern-day and next-generation wireless systems.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Using Machine Learning Algorithms for Anomalies Detection in Modern Wireless Communication Systems

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Rume Elizabeth Yoro,
  • Fatimah Adamu-Fika,
  • Adeniran Kolade Ademuwagun,
  • Osichinaka Ubadike,
  • Zakka Augustine,
  • Tolulope Olushola Olufemi,
  • Philip Achimugu

摘要

Anomalies experienced in wireless communication systems have been a thing of serious concern. These anomalies present themselves as signal distorters in the forms of impairment, attenuation, interference, and many more. As such, this research adopted the use of the machine learning (ML) algorithm, a sub-field of artificial intelligence (AI) to explore and correct some anomalies experienced in the physical layer of wireless communications systems. These anomalies are the discrepancies observed between the transmitted signal waveform and the received signal waveform, but in this research work, the focus is on interference anomalies that degrade the quality and performance of the wireless communication systems. This activity would be performed in the Channel Estimation Region (CER) of a Feedback Filtered Orthogonal Frequency Division Multiplexing (FF-OFDM) induced waveform because of its scalability in driving variable Tone Spaces (TSs) and in extension varying air interfaces. Results obtained showed an interference anomalies accuracy detection of 98%, specificity of 0.9545%, and sensitivity of 1.000%. This high efficiency is obtained by the hybridization of the Naïve Bayes—Support Vector Machine (NB-SVM) method of Supervised Learning (SL) algorithms of ML. These results simply suggest that the deployment of AI in wireless technology as proposed by Third Generation Partnership Project (3GPP) to activate Fifth Generation (5G) New Radio (NR) Frequency Two-Advanced (FR2-A) waveform has brought a limelight in interference anomalies detection and mitigation, suitable for deployment in the modern-day and next-generation wireless systems.