Detalhes bibliográficos
| Ano de defesa: |
2024 |
| Autor(a) principal: |
Oliveira , Danilo Machado
 |
| Orientador(a): |
Mafra , Samuel Baraldi
|
| Banca de defesa: |
Não Informado pela instituição |
| Tipo de documento: |
Tese
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
por |
| Instituição de defesa: |
Instituto Nacional de Telecomunica????es
|
| Programa de Pós-Graduação: |
Mestrado em Engenharia de Telecomunica????es
|
| Departamento: |
Instituto Nacional de Telecomunica????es
|
| País: |
Brasil
|
| Palavras-chave em Português: |
|
| Área do conhecimento CNPq: |
|
| Link de acesso: |
https://tede.inatel.br:8080/tede/handle/tede/262
|
Resumo: |
Public health authorities in Brazil face significant challenges in combating the Aedes aegypti mosquito, which poses a threat to the population. Despite efforts such as awareness campaigns and control measures, diseases such as dengue, Zika virus and chikungunya prevail. However, technological advances have allowed the development of devices capable of detecting the female mosquitoes Aedes aegypti , which are the main vectors of these diseases. This work proposes an Internet of Things (IoT) system and weather stations to effectively monitor and control the insect population, especially in high-risk areas, through the implementation of smart pest control traps, based on Computer Vision. The intelligent system features the YOLOv7 (You Only Look Once v7) algorithm that is capable of detecting and counting insects in real time, combined with LoRa/LoRaWan connectivity and IoT system intelligence. The proposed trap solution enables continuous data collection and implementation of advanced analytics, with Machine Learning (ML) and Deep Learning (DL), to improve the accuracy and efficiency of the detection system. This adaptive approach is effective in combating Aedes aegypti mosquitoes in real time. Keywords: Ae.aegypti, Computer Vision, IoT, Internet of Things, LoRa, LoRaWAN, Machine Learning, Smart Traps, YOLOv7. |
