NORMA eResearch @NCI Library

Smart Farming IoT sensor data filtering using Pattern Analysis and Edge computing to reduce latency

Patil, Priya Pramod (2022) Smart Farming IoT sensor data filtering using Pattern Analysis and Edge computing to reduce latency. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


From prehistoric times to the present, agriculture has always played an important role because of how crucial it is to the continued existence of humans. Given the world’s expanding population, it is essential to increase agricultural output. The lack of available resources and severe weather has only made matters worse. By combining conventional farming practices with innovations like the Internet of Things (IoT), artificial intelligence (AI), and cloud computing, ”smart farming” allows farmers to increase their harvest quality and longevity while still coming close to their crops’ full yield potential. Because IoT devices generate so much data, it is not a good idea to transfer all redundant data from IoT sensors to the cloud and risk experiencing latency issues. Data filtering based on patterns can be done locally on the device or at the edge to conserve bandwidth. As a result, this study proposes that pattern recognition be used to eliminate redundancy before data enters the cloud rather than after it arrives. This will be demonstrated by developing a Farm Cloud Solution (FCS) method which focuses on removing the excess redundant data from the temperature and moisture readings gathered from four different farms within the vicinity. The FCS method involves pre-processing with repetition removal (RR), invalid data removal (IDR), and linear redundancy removal (LRR). A minimum 28.6 % improvement in the latency and more than 5700 bytes were saved from an average of 16136 bytes of data, roughly 35% of the data. The error is allowed within a reasonable 1% margin, allowing the farmer to forecast the upcoming harvest. Less data was sent to the cloud while retaining all vital information This FCS algorithm is a unique approach to two-tier architecture and could potentially prove to be the best option for smart farming technology.

Item Type: Thesis (Masters)
Heeney, Sean
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry
T Technology > T Technology (General) > Information Technology > Cloud computing
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Tamara Malone
Date Deposited: 19 Apr 2023 11:53
Last Modified: 19 Apr 2023 11:53

Actions (login required)

View Item View Item