Desarrollo de una aplicación móvil para el monitoreo de la calidad del aire en Quito
The effects of the rapid growth of the world population turn into excessive use and scarcity of natural resources, deforestation, climate change and especially environmental pollution. Currently, more than half of the worlds population lives in urban areas, and this number is expected to grow to abo...
Đã lưu trong:
| Tác giả chính: | |
|---|---|
| Định dạng: | bachelorThesis |
| Ngôn ngữ: | spa |
| Được phát hành: |
2019
|
| Những chủ đề: | |
| Truy cập trực tuyến: | http://dspace.udla.edu.ec/handle/33000/10780 |
| Các nhãn: |
Thêm thẻ
Không có thẻ, Là người đầu tiên thẻ bản ghi này!
|
Thêm thẻ | Tóm tắt: | The effects of the rapid growth of the world population turn into excessive use and scarcity of natural resources, deforestation, climate change and especially environmental pollution. Currently, more than half of the worlds population lives in urban areas, and this number is expected to grow to about 66 percent by 2050, mainly due to urbanization trends in developing countries. A recent study on air quality in Quito, the capital of Ecuador, coincides at long-term levels. Higher than the national standards of 15 g-m3. The situation has diminished due to the efforts of local and national governments in the last decade, in some places of the city. The latter reflects the global trends of urbanization. It is also based on the use of different monitoring stations distributed in certain parts of the city by the Ministry of Environment. Also applies Machine Learning to obtain a more accurate model. Currently, there is no such solution in the country, by detecting events locally in the device itself. This is a way of demonstrating that there is a solution for users not to expose themselves to high levels of pollution and in this way to provide greater privacy, as well as a sensible use of resources. To obtain the information, several modules were executed in the application for the data collection, which were obtained by the following methods are detailed: the data of the time administered by Google Maps, the handling of (Inverse Distance Weighting IDW), method used for the interpolation between the user's location and the monitoring stations. With the results, a model was developed and a supervised learning technique with better performance was obtained. |
|---|