MONKEY-POX VIRUS DETECTION USING PRE-TRAINED DEEP LEARNING BASED APPROACHES

Computer Engineering

The monkey-pox virus is slowly spreading around the world. This paper discusses discovering and identifying the monkey-pox virus using pre-trained deep learning-based approaches. The huge epidemic of this sickness has sickened thousands of people and even resulted in deaths. The disease's effects may last up to three or four weeks in a patient. Symptoms include skin rash or mucosal lesions, fever, headache, muscle aches, back discomfort, fatigue, and enlarged lymph nodes. Monkey-pox can spread to humans by personal contact with an infected individual or with contaminated objects. So, detecting the virus early is critical to prevent community transmission. Deep learning-based detection could provide a solution to this problem. Deep learning techniques could help in discovering the disease early and avoiding transmission. The pre-trained model is used in the dataset to reliably identify significant patterns and features. To improve the model's performance, data augmentation is implemented. The experiment is carried out on a dataset containing images of monkey-pox, and accuracy of the model is evaluated. The results indicate that the recommended deep learning approach surpasses previously suggested models, demonstrating its reliability as a efficient tool for detecting the monkey-pox virus. This technique is effective in assisting healthcare workers in making fast and accurate diagnoses.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.