A smart fish feeding system for internet of things based aquariums

Effective fish feeding within aquarium environments is essential for proper health and growth of fishes. However, due to busy lifestyles, maintaining proper feeding cycles is a key challenge for aquarium owners. With the emergence of technologies including Internet of Things, various smart aquarium solutions have emerged. However, within existing solutions and published literature, limited work has been done to automate fish feeding for smart aquariums. As such, this paper extends literature on automated fish feeding within IoT-based aquariums through the implementation and evaluation of such a fish-feeding algorithm and system. In this study, a fish feeding algorithm that computes various aspects related to fish feeding (e.g. feeding time and number of pellets) is presented, based on aquarium environmental parameters (e.g. temperature and pH) along with aquarium characteristics (e.g. fish species and density). Based upon the proposed algorithm, a smart fish feeding solution was designed and implemented. For evaluation, the algorithm and system were tested within five aquariums to determine their effectiveness in feeding fish within different aquarium settings. Results showed that precision and recall reduce with increased number of fish species. Based on these limitations, recommendations have been made to enhance the implementation of such systems.

© 2020 ACM. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications, http://dx.doi.org/10.1145/3415088.3415119