By: Bassalel Biju, Amaldev H., Mohammed Rezin S., B. Sivaganga, Abdhulla Navas, and Thasreef H.R.
1-5-Students, Department of Electronics and Electrical Engineering, College of Engineering Perumon, Kollam, Kerala, India
6-Assistant Professor, Department of Electronics and Electrical Engineering, College of Engineering Perumon, Kollam, Kerala, India
The World Mosquito Programme highlights the significant global threat posed by dengue fever, estimating that over half of the world’s population is at risk, with approximately 390 million cases reported annually. In 2023, India witnessed a substantial increase in dengue cases, recording over 270,000 cases compared to 74,000 in 2017. Dengue Virus (DENV) transmission occurs through Aedes Aegypti Mosquito bites, and with no specific treatment or vaccine available, effective management and prevention are crucial for public health. To address this, an engineering solution is proposed to eliminate Aedes Aegypti Mosquitoes, primarily found in areas such as harbours and stagnant waters. The solution involves an electric fence equipped with UV LED technology to attract mosquitoes, with captured images analysed using Artificial Neural Network (ANN) techniques. The suggested approach seeks to transform conventional mosquito control techniques by utilizing AI and image processing technologies. By training the network with images of Aedes Aegypti and similar species, mosquitoes are accurately identified and subjected to electrification upon detection, facilitated by a Raspberry Pi supporting the ANN technology. This innovative approach aims to mitigate the risk of dengue transmission in high-risk areas such as hospitals, residential buildings, and communal spaces.
Keywords: Dengue fever, Aedes Aegypti Mosquito, Image processing, ANN technology, Raspberry Pi.
Citation:
Refrences:
- Jahangir Alam S.M., H. Guoqing, and C. Chen” Characteristics Analysis and Detection Algorithm of Mosquitoes,” TELKOMNlKA Indonesian Journal of Electrical Engineering Volume 12 (7), 5368-5378.
- John Wiley & Sons “Practical Image and Video Processing Using MATLAB,”, Inc., Hoboken, New Jersey. Marques, O. (20 II)
- Ayan kumar Biswas, Nahianalam siddique, Bing Bang Tian, EnochWong and Kevin A Caillout “Design of a Fiber-Optic Sensing Mosquito Trap”, IEEE sensors journal, vol.13, issue: 11, pp. 45-50 March 2014.
- Simarjit Singh Saini, Divya Bansal, Gurnoor Singh Brar, EkambirSidhu, “Solar Energy Driven Arduino based Smart Mosquito Repeller System”, IEEE WiSPNET,2016.
- Rumali Siddiqua, Shakila Rahman and Jia Uddin, ” Mosquito Detection Method Using Faster R-CNN and Image Processing Techniques”, Annals of Emerging Technologies in Computing (AETiC) Vol. 5, No. 3, 2021
- Anna Monica M. De Los Reyes, Anna Camille A. Reyes, Jumelyn L. Torres, Dionis A. Padilla, Jocelyn Villaverde ” Detection of Aedes Aegypti Mosquito by Digital Image Processing Techniques and Support Vector Machine “, Computer Engineering Department, School 0/ EECE Mapua Institute a/Technology Muralla St., Intramuros, Manila
- Liu WL, Wang Y, Chen YX, Chen BY, Lin AY, Dai ST, Chen CH, Liao LD. An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance. Frontiers in Bioengineering and Biotechnology. 2023 Jan 20;11:1100968.
- Adhane G, Dehshibi MM, Masip D. A deep convolutional neural network for classification of aedes albopictus mosquitoes. IEEE Access. 2021 May 12;9:72681-90.
- Lee KY, Chung N, Hwang S. Application of an artificial neural network (ANN) model for predicting mosquito abundances in urban areas. Ecological informatics. 2016 Nov 1;36:172-80.
- Fernandes MS, Cordeiro W, Recamonde-Mendoza M. Detecting Aedes aegypti mosquitoes through audio classification with convolutional neural networks. Computers in Biology and Medicine. 2021 Feb 1;129:104152.
