CSBPNN VS BPNN Machine Learning Network Models Significant Assessment to Lung Cancer Recognition System

@article{1714300,
      author = {Oluwafemi J. Ayangbekun, Wilson Sakpere, Oladunni A. Akanni},
      title = {CSBPNN VS BPNN Machine Learning Network Models Significant Assessment to Lung Cancer Recognition System},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {8},
      pages = {505-513},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1714300.pdf},
      abstract = {Cancer of the lung have been regarded as one of the most dangerous widespread type of cancer that needed to be addressed clinically using computational intelligence. In this paper, total datasets of 893 CT lung images were collected which comprises of 200 Benign, 393 of Malignant and 300 of Normal lung dataset. The analytical performance evaluation of Back Propagation Neural Network (BPNN) technique and Chameleon Swarm (CS) Optimization technique on Lung cancer prevalence was applied and yielded significant results. CSBPNN shows better performance and significant improvement than the BPNN with 98.20% accuracy level at precision time of 38.86secs compared with BPNN with 97.40% and 59.89secs accuracy and recognition time respectively. Furthermore, the evaluation results in terms of FPR, Specificity and Sensitivity metrics produces 0.33%, 99.67% and 96.95% respectively for CSBPNN indicating better performance; compared with 1.00% FPR, 99.00% Specificity and 95.42% Sensitivity values. With the results obtained, the Chameleon Swarm Optimization technique outperformed the Back Propagation Neural Network technique in predicting and classifying lung cancer images. This was evident in the higher accuracy and precision scores of the Chameleon Swarm Optimization technique. Additionally, the Chameleon Swarm Optimization technique also showed better performance in terms of sensitivity and specificity compared to the BPNN technique. These results emphasise even more possibilities of the Chameleon Swarm Optimization technique to raise the lung cancer diagnostic and treatment accuracy. Thus, the study contributes to the existing literatures on the application of swarm optimization techniques in the field of medical research.},
      keywords = {BPNN, CSBPNN, Lung Cancer, Optimization, Metrics, Performance},
      month = {February},
  }