Identifying highly vulnerable mosquito breeding sites using machine learning and drone based aerial survey

Shyam V. Sundhar; Indhiya V. N Selvan; S. Sanjeevi Prasad; S. Hariharan; Rashi Agarwal

doi:10.53730/ijhs.v6nS3.5263

Authors

Shyam Sundhar V.
Shyamsundhar35@gmail.com
Research Scholar, Department of Geography, University of Madras, Chennai, India
Indhiya Selvan V. N Research Scholar, Department of Geography, University of Madras, Chennai, India
S. Sanjeevi Prasad Assistant Professor, Department of Geography, University of Madras, Chennai, India
Hariharan S. Student, M. Tech Geoinformatics, Department of Geography, University of Madras, Chennai, India
Rashi Agarwal Department of CSE, UIET, Chhatrapati Shahu Ji Maharaj University, Kanpur, India

Keywords:

drone survey, GIS, health geography, machine learning, remote sensing

Abstract

This study deals with Drone based Aerial Survey in analyzing and identification of highly vulnerable mosquito breeding sites at Buckingham canal Chepauk, Chennai. It is small section of Buckingham canal studied using the drone for capturing the images and furtherly images were processed for identifying the sites prone to breeding of mosquitos. Approach used here of capturing images and classifying the vulnerable sites, using a machine learning approach in for extracting features using the algorithm and later generating a Support Vector Machine to train and classify the images. Tensorflow object detection algorithm was used to detect the object and also generate the probability level. Tensorflow based supervised classification involves stacking multiple layers of neural network for a classification. Methods like back propagation invoked in the neural networks ensures the classification accuracy are increased. In this algorithm Single shot multi box detector (SSD) has been used which provides fast detection. Single shot multi box detector (SSD) method is based on a feed-forward convolutional network, followed by a non-maximum suppression step to produce final detections. The accuracy constraint of 70% was kept for qualifying as a potential site to negate ambiguities arising due to processing errors.

Downloads

Download data is not yet available.

References

Amarasinghe, A., Suduwella, C., Niroshan, L., Elvitigala, C., De Zoysa, K., & Keppetiyagama, C. (2017, September). Suppressing dengue via a drone system. In 2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer) (pp. 1-7). IEEE.

Rani, A., Gupta, A., Nagpal, B. N., & Mehta, S. S. (2018). Mosquito borne diseases and sanitation in Ghaziabad district, Uttar Pradesh, India. Int J Mosquito Res, 5(5), 25-30.

Agarwal, A., Chaudhuri, U., Chaudhuri, S., & Seetharaman, G. (2014, July). Detection of potential mosquito breeding sites based on community sourced geotagged images. In Geospatial InfoFusion and Video Analytics IV; and Motion Imagery for ISR and Situational Awareness II (Vol. 9089, p. 90890M). International Society for Optics and Photonics.

Annadurai, K., Danasekaran, R., Mani, G., & Ramasamy, J. (2015). Mosquito menace: A major threat in modern era. Medical Journal of Dr. DY Patil University, 8(3), 414-414.

Amarasinghe, A., Suduwella, C., Elvitigala, C., Niroshan, L., Amaraweera, R. J., Gunawardana, K., ... & Keppetiyagama, C. (2017, November). A machine learning approach for identifying mosquito breeding sites via drone images. In Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems (pp. 1-2).

Kim, B. K., Kang, H. S., & Park, S. O. (2016). Drone classification using convolutional neural networks with merged Doppler images. IEEE Geoscience and Remote Sensing Letters, 14(1), 38-42.

Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2), 91-110.

Sreeram, S., & Shanmugam, L. (2018, June). Autonomous robotic system based environmental assessment and dengue hot-spot identification. In 2018 IEEE International Conference on Environment and Electrical Engineering and 2018 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe) (pp. 1-6). IEEE.

Mehra, M., Bagri, A., Jiang, X., & Ortiz, J. (2016, June). Image analysis for identifying mosquito breeding grounds. In 2016 IEEE International Conference on Sensing, Communication and Networking (SECON Workshops) (pp. 1-6). IEEE.

Renwick, J. D., Klein, L. J., & Hamann, H. F. (2016, December). Drone-based reconstruction for 3D geospatial data processing. In 2016 IEEE 3rd World Forum on Internet of Things (WF-IoT) (pp. 729-734). IEEE.

Suduwella, C., Amarasinghe, A., Niroshan, L., Elvitigala, C., De Zoysa, K., & Keppetiyagama, C. (2017, June). Identifying mosquito breeding sites via drone images. In Proceedings of the 3rd Workshop on Micro Aerial Vehicle Networks, Systems, and Applications (pp. 27-30).

“Handbook for Integrated Vector Management.” World Health Organization. World Health Organization. Accessed January 15, 2022.http://apps.who.int/iris/bitstream/handle/10665/

Vo, X. T., & Jo, K. H. (2021). Accurate Bounding Box Prediction for Single-Shot Object Detection. IEEE Transactions on Industrial Informatics.

“Executive Summary.” World Health Organization. World Health Organization, July 29, 2013. https://www.who.int/whr/1996/media_centre/executive_summary1/en/.

Kumar, D. S., Andimuthu, R., Rajan, R., & Venkatesan, M. S. (2014). Spatial trend, environmental and socioeconomic factors associated with malaria prevalence in Chennai. Malaria Journal, 13(1), 1-9.