<![CDATA[Neisseria gonorrhoeae (gonococcus) is the primary bacterium responsible for the sexually transmitted infection gonorrhea, which is transmitted through sexual contact. Traditional identification methods, such as Polymerase Chain Reaction (PCR), are still widely used but have limitations in terms of cost, time, and the need for multiple reagents. This study aims to develop a faster and more efficient identification method using Artificial Intelligence (AI) through a Convolutional Neural Network (CNN) approach based on the Inception V3 architecture. The dataset used consists of 84 JPEG images, comprising 42 images of Neisseria gonorrhoeae and 42 non-Neisseria images. The model was trained using 50 epochs with an early stopping mechanism, which optimally halted at epoch 25, achieving a training accuracy of 94.74% and a validation accuracy of 100%. The resulting model achieved 96% classification accuracy, correctly identifying all 8 positive and 4 negative test images. These findings indicate that CNN based on Inception V3 is effective in classifying Neisseria gonorrhoeae images and has strong potential as a fast, accurate, and efficient diagnostic alternative.]]>
