Every year about one million people die due to diseases transmitted by mosquitoes. The infection is transmitted to a person when an infected mosquito stings, injecting the saliva into the human body. The best possible way to prevent a mosquito-borne infection till date is to save the humans from exposure to mosquito bites. This study proposes a Machine Learning (ML) and Deep Learning based system to detect the presence of two critical disease spreading classes of mosquitoes such as the Aedes and Culex. The proposed system will effectively aid in epidemiology to design evidence-based policies and decisions by analyzing the risks and transmission. The study proposes an effective methodology for the classification of mosquitoes using ML and CNN models. The novel RIFS has been introduced which integrates two types of feature selection techniques – the ROI-based image filtering and the wrappers-based FFS technique. Comparative analysis of various ML and deep learning models has been performed to determine the most appropriate model applicable based on their performance metrics as well as computational needs. Results prove that ETC outperformed among the all applied ML model by providing 0.992 accuracy while VVG16 has outperformed other CNN models by giving 0.986 of accuracy.

每年约有一百万人死于蚊子传播的疾病。当受感染的蚊子叮咬并将唾液注入人体时，感染就会传播给人。迄今为止，预防蚊媒感染的最佳方法是使人类免于接触蚊虫叮咬。本研究提出了一种基于机器学习 (ML) 和深度学习的系统，以检测伊蚊和库蚊等两种关键疾病传播类蚊子的存在。拟议的系统将有效地帮助流行病学通过分析风险和传播来设计基于证据的政策和决策。该研究提出了一种使用 ML 和 CNN 模型对蚊子进行分类的有效方法。引入了新颖的 RIFS，它集成了两种类型的特征选择技术——基于 ROI 的图像过滤和基于包装器的 FFS 技术。已经对各种 ML 和深度学习模型进行了比较分析，以根据它们的性能指标和计算需求确定最合适的模型。结果证明，ETC 在所有应用的 ML 模型中表现优于所有应用的 ML 模型，准确度为 0.992，而 VVG16 的准确度为 0.986，优于其他 CNN 模型。