Analysis of the Performance for Quality of Transmission in Optical Fiber Communication Based on Machine Learning Optimization

@article{1710110,
      author = {Folakemi Judith Omogoroye, Guiawa Mathurine, Olubunmi Adewale Akinola, Onyegbadue Ikenna Augustine, Fred Izilein},
      title = {Analysis of the Performance for Quality of Transmission in Optical Fiber Communication Based on Machine Learning Optimization},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {2},
      pages = {873-879},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710110.pdf},
      abstract = {The foundation and application of optical communication networks is the estimation of the optical signal?s Quality of Transmission (QoT) parameters from source to destination nodes. However, Machine Learning (ML) approaches are being used in recent research to increase the accuracy of QoT estimation. In this study, the performance validation was carried out through the application of ML computational technique and the results demonstrated a stable Bit Error Ratio (BER) of ~10??? and a consistent Signal-to-Noise Ratio (SNR) of 12.6?13.2 dB across transmission distances 19?22 km. In addition, the Phase-Shift Keying (PSK) and the Quadrature Phase-Shift Keying (QPSK) modulation outperformed the Amplitude Shift Keying (ASK) and Frequency Shift Keying (FSK), with statistical significance confirmed via chi-square tests. Conclusively, comparative advantages surpassed prior studies in BER reduction, SNR efficiency and multi-modulation adaptability.},
      keywords = {Artificial Intelligence; Communication; Optical fiber; Machine learning; Modelling; Transmission},
      month = {August},
  }