Clean water is one of the essential things in life. The running water in natural forms is considered as clean water. To avoid exposure to countless diseases, it is imperative to separate stagnant water from clean water. Thus the main objective of the proposed paper is to create an image dataset of stagnant water and wet surface to detect stagnant water. Accordingly, we considered stagnant water images in different forms and sizes to construct the dataset. In addition to that, brown and black earth surface is considered for the wet surface detection. The dataset consists of 1976 labeled images captured from various angles with annotated files. The dataset images are labelled for two classes, namely water and wet surface. This dataset is highly useful for deep learning experts working in the field of disease control management and post-rainfall earth surface monitoring.
Objective: Mosquito breeding site detection is crucial due to the colorization of water. Most systems fail to identify different types of stagnant water; hence, accurate water identification is essential. This study aims to devise an approach that can help increase the accuracy of detecting and distinguishing stagnant water from that of other wet surfaces. Methods: This work has proposed a technique using anchor boxes to reduce misclassification for detecting stagnant water. The images were collected for different types of water. The dataset was manually created by labeling images. Findings: We evaluated the proposed approach's results and discovered that changing the anchor size and increasing training iterations on the dataset reduced misclassification by 89.20%. Novelty: The proposed method improves accuracy by using suitable anchor boxes to distinguish the water body from the wet surface. Unlike existing systems that are only capable of detecting a particular type of water; the improved YOLO V3 detects wet surfaces and different types of stagnant water due to training on a real-time customized dataset.
Vector-borne disease control is an important issue faced by mankind. Many existing systems perform the detection and prevention of mosquito breeding sites using UAVbased methods. However, they don't provide real-time monitoring and detection of the same on daily basis. This study proposes a cloud-based deep-learning system to control the disease spread at a high scale. The implemented system does continuous monitoring using the existing public cameras for the potential mosquito breeding hotspots, further, the corresponding location coordinates will be forwarded to the local authorities. A history of the location coordinates maintained at the remote server will help monitor hotspots. We evaluated the current approach results and discovered that by layer pruning, the accuracy is improved by 14% and further reduces execution time by 10 sec. For accuracy and execution time calculation, the pruned model was tested on the validation dataset, and then the comparison was done with the original deep learning model. This indicates that the system can accurately detect the number of potential mosquito breeding sites. These results are expected to support decision-making on rapid resource allocation for vector control actions on a regular basis by achieving the sustainability goal of UNSDG (3).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.