A Robust Development to Predict Black Fungus Disease with Enhanced Learning Principles

Presently, a very visible virus known as COVID-19 is afflicting nations all over the globe. This illness has caused several deaths and is still causing problems in most nations. The initial wave of the COVID-19 pandemic was so deadly that it devastated whole countries and devastated economies throughout the globe. In 2021, during the second wave of the COVID-19 pandemic (April–July), a potentially fatal illness known as Mucormycosis (also dubbed black fungus) was found all across the globe. By analyzing the mood of social media data, we can learn how the public views these pandemics. Fungus causes a wide range of infections that can be fatal to people, and it is very unpleasant and harmful to human health. There are many of types of fungus, and spores are always floating around. Its symptoms and signs are not specific. A fungal infection manifests itself with a variety of symptoms, including but not limited to: nasal and eye discoloration, double or blurred vision, chest discomfort, difficulty breathing, fever, and cough. Using a fungus detection system and algorithms that automatically identify fungus using machine and deep learning approaches, this study primarily aims to analyze and estimate the infection likelihood based on black fungus photos. Presenting Hybrid Learning based Fungus Identification (HLFI), a new algorithm for black fungus prediction that relies on deep learning; this paper also introduces the more traditional Convolutional-Neural-Network (CNN) as a learning model to assess the efficacy of the proposed scheme.