Project 1: Sensor Based Aquaponics Fishpond Datasets: IoT Fishpond Monitoring Datasets

Funded by: Lacuna Fund 2020, USA. Grant No.: 0326-S-001, 2020. PI: Collins N.Udanor

Using my skills in IoT and cloud computing I designed and developed an Internet of Things (IoT) sensor system consisting of an ESP-32 microcontroller (a kind of computer in a chip) which controls water quality sensors in aquaponics (a type of fish farming that include the planting of vegetables without soil but using the fishpond wastewater) fishponds for automatic data collection.

The sensors included temperature, pH, dissolved oxygen, turbidity, ammonia and nitrate sensors. The IoT system reads water quality data and uploads the same to the cloud in real time. The process of using the IoT sensors to collect data begins with identifying the right sensor, procuring and testing them on practice workbench. After which the sensors are hardwired to the circuit board, connected to the computer and codes written in Arduino software development kit (SDK) is transferred from the computer into the microcontroller. When the sensors are placed inside the fishpond, they collect water quality data and transmits same to a cloud computing repository. The dataset is visualized in the cloud and downloaded for the purposes of machine learning for yield prediction.

The insights such dataset will provide when subjected to machine learning and data analytics is very useful to fish farmers, informing them when to change the pond water, what number of fish to stock in a given pond size, provide knowledge about feed conversion rates, and predict the growth rate and patterns of their fishes. I was also able to build a mobile app from the machine learning mode that enables fish farmers to monitor and predict the growth of their fish.

 

Repository name: Kaggle Direct link to the dataset: https://www.kaggle.com/dataset/e81da8b7666dc7af41cdc3aa5ef96c5547e4f412598a030f40d444550965e34fData identification number (DOI): 10.34740/kaggle/dsv/2681778

Publications:

  1. H. Eneh, C.N. Udanor, N.I. Ossai, S.O. Aneke, P.O. Ugwoke, A.A. Obayi, C.H. Ugwuishiwu, G.E. Okereke (2023), Towards an improved internet of things sensors data quality for a smart aquaponics system yield prediction, MethodsX, Volume 11, 2023, 102436, ISSN 2215-0161, https://doi.org/10.1016/j.mex.2023.102436. (https://www.sciencedirect.com/science/article/pii/S2215016123004326) – published journal paper
  2. C.N. Udanor, N.I. Ossai, E.O. Nweke, B.O. Ogbuokiri, A.H. Eneh, C.H. Ugwuishiwu, S.O. Aneke, A.O. Ezuwgu, P.O. Ugwoke, Arua Christiana (2022). An internet of things labelled dataset for aquaponics fishpond water quality monitoring system, Data in Brief, Volume 43, 108400, ISSN 2352-3409, https://doi.org/10.1016/j.dib.2022.108400. (https://www.sciencedirect.com/science/article/pii/S2352340922005972) – published journal paper
  3. C.N. Udanor, N.I. Ossai, B.O. Ogbuokiri, O.E. Nweke, P.O. Ugwoke, U.K. Ome (2021). A Pilot Implementation of a Remote IoT Sensors for Aquaponics System Datasets Acquisition, The Journal of Computer Science and it’s Applications (JCSA), Vol. 28, Iss. 2. https://dx.doi.org/10.4314/jcsia.v28i2.1 – published journal paper