| Pub. Date | : Jan, 2022 |
|---|---|
| Product Name | : The IUP Journal of Computer Sciences |
| Product Type | : Article |
| Product Code | : IJCS40122 |
| Author Name | : R Ajikaran, P Vigneshwaran and J Charles |
| Availability | : YES |
| Subject/Domain | : Management |
| Download Format | : PDF Format |
| No. of Pages | : 16 |
The fish egg counting technique is important in fisheries research because it allows researchers to better grasp the pattern and organization of fish egg development and provide a platform for fish larvae stock monitoring. Previously, the process of fish eggs was monitored using a microscope and a human-held gadget, which was a labor-intensive and time-consuming activity. Furthermore, while the manual method is useful for counting a tiny sample size, the process of counting larvae becomes more difficult when the sample size is big (Cadena-Herrera et al., 2015). All these deficiencies will affect the process of counting fish eggs; hence, improvement of the traditional method of counting using computer-based technology is required.
Serverless computing differs from traditional cloud computing concepts in the sense that the infrastructure and platforms are running are transparent to customers. In this approach, the customers are only concerned with the desired functionality of their application and the rest is delegated to the service provider.
When the rate of data expansion outpaces the number of available servers, the demand for a cloud solution leads to the adoption of serverless computing systems for a variety of applications. This cutting-edge approach to data storage has helped to eliminate the costs associated with the upkeep of physical storage systems (Rolle, 2018).
Fish egg counting, Automation, Deep learning, Convolution Neural Network (CNN), Aquaculture