Multi-protocol IOT Gateway

Precision Agriculture

Precision Agriculture

Smart Farming

1- Abstract

Farming involves complex processes ranging from adjusting fertilizers, conducting the proper pesticides, adjusting adequate irrigation periods, etc.
New growing methods like Hydroponics, Aquaponics, and Aeroponics are considered as the most efficient and futuristic methods for urban farming and recommended by NASA to yield to healthier and more productive.
Get insightful analysis for crops’ status, and deficiencies facilitate an early decision or even new strategy acquisition. These insights require data availability which can be collected through different types of sensors serving different purposes.
Artificial intelligence (AI) and machine learning are the perfect tools to be deployed in a smart farming environment since an enormous amount of data would be available.

2- Problem Statement

The objective of this project is to develop a small-scale smart farm where a set of different sensors will be distributed in such a way to collect data and measurements from different nodes. The collected data will be uploaded to a cloud-based server for processing.
The collected data can be classified into two main types; the first type is measurements and the second type is images which require further image processing for data extraction.
Finally, collected measurements, data, and their extracts will be used for training purposes to build an AI network.

3- Milestones

• Building a monitoring and a control system for an indoor/outdoor farm serving the following purposes,
              o Control of soil moisture, weather temperature, and humidity, PH dosing, water TDS/nutrients.
              o Light luminosity sensing.
              o VOC (volatile organic compounds) sensing.
• Developing a cloud-based processing/visualization platform for the aggregated data.
• Image processing and analysis for images collected from an optical sensing device, e.g., NIR.
• Predictive analysis of the aggregated data for early decision making and deficiencies identification.

4- Key Resources Required

  • Embedded system engineers with excellent skills in C programming, HW interfacing, and algorithms development.
  • Machine Learning for classification, regression, neural networks, and image processing developers.
  • Cloud and web development skills: Python, JavaScript, TSQL.

5- Selection Criteria

  • Qualified candidates have to show their skills set and how it fits the requirements and the activities designated for this project.
  • It is highly recommended for students majoring in Computer Engineering, Computer Science, and Communications Engineering graduating in 2019.