Recognizing of gastrointestinal disorder using convolutional neural network in comparison with multi-information fusion network

The primary objective of this research is to enhance the accuracy of gastrointestinal disorder recognition by employing novel Convolutional Neural Networks (CNN) over Multi-Information Fusion Network. The research utilizes a dataset comprising endoscopic images of store item demand. Two distinct groups were selected for the study, each consisting of 20 samples. The chosen machine learning algorithms for this approach are Convolutional Neural Networks and Multi-Information Fusion Networks. Statistical analysis employed a G-power value of 80% and a 95% confidence interval (CI) for SPSS calculations. The key finding of the study indicates that the novel Convolutional Neural Network obtained an accuracy rate of 93.6220%, outperforming the Multi-Information Fusion Network with an accuracy of 92.5250%. The independent sample t-test yielded a statistical significance value of p=0.001 (p<0.05) between the two groups. This research introduces a robust framework for the identification of gastrointestinal disorders from the selected dataset, utilizing two distinct classifier algorithms. Notably, the CNN classifier exhibits significantly higher accuracy compared to the Multi-Information Fusion Network classifier.