Computational intelligence-based automation and control for adaptive management system (AMS) of a smart aquaponics
As the population is expected to increase to 9.8 billion in 2050, according to the United Nations, there is an increasing demand for food and space due to the continuous increase of population density. This causes rural areas which were originally the base for agricultural development to be transfor...
Saved in:
| Main Author: | |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
2021
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etdm_ece/2 https://animorepository.dlsu.edu.ph/cgi/viewcontent.cgi?article=1000&context=etdm_ece |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | As the population is expected to increase to 9.8 billion in 2050, according to the United Nations, there is an increasing demand for food and space due to the continuous increase of population density. This causes rural areas which were originally the base for agricultural development to be transformed into urban areas. Urbanization now causes food insecurity. Addressing the issues on urbanization, urban farming has now become a feasible solution to meet the growing demand of food and space. Providing a Close Environment Agriculture (CEA) is both a challenge and a solution in facing development and establishment of urban farms. An Adaptive Management System (AMS) is necessary to operate such systems to provide an artificial environment suitable to grow and produce cultivars effectively resulting in sustainable efficiency. This research proposes the development of a computational intelligence-based automation and control system utilizing machine and deep learning models for evaluating product quality. Quality assessments are then used for adjusting the environmental parameters with respect to the cultivars’ needs. The system is to be composed of sensors for data acquisition, as well as actuators for model-dictated responses to stimuli. Data logging will be done wirelessly through a router which would collect and monitor data through a cloud-based dashboard. The model that will undergo training from the data acquired will undergo statistical comparative analysis and least computational cost analysis to improve the performance. System performance will also be evaluated with the monitoring of the status and conditions of the sensors and actuators. |
|---|