No abstract

Shrimp cultivation is a very profitable business in Gresik. However, shrimp farmers in Mojopuro Gede Village, Gresik admitted that they did not optimize their cultivation process. The farmer did not realize that water quality is essential to be considered in aquaculture. Based on these problems, the team held a community service in Mojopuro Gede Village, Gresik by introducing the water quality meter module and giving it to several shrimp farmers in the area. This activity was carried out so that the farmers can improve their cultivation process which has not been optimal and also introduce them to technological developments. Technology use in cultivation is expected to increase the quality of the farmers' crops. The implementation methods used in this activity are socialization and training. In this community service program, education has been given to the farmers so that they understand and care about the condition of their ponds in the cultivation process. The purpose of this program is for introducing the importance of technology in the cultivation process, even though it is actually not easy to provide education to shrimp farmers, especially traditional farmers. Therefore, related parties (NU Gresik Maritime Institute and Maritime Affairs and Fisheries Office of East Java Province) are expected to be more active in providing understanding to the farmers regarding the importance of applying technology in the cultivation process.

In some cases, image processing relies on a lot of training data to produce good and accurate models. It can be done to get an accurate model by augmenting the data, adjusting the darkness level of the image, and providing interference to the image. However, the more data that is trained, of course, requires high computational costs. One way that can be done is to add acceleration and parallel communication. This study discusses several scenarios of applying CUDA and MPI to train the 14.04 GB corn leaf disease dataset. The use of CUDA and MPI in the image pre-processing process. The results of the pre-processing image accuracy are 83.37%, while the precision value is 86.18%. In pre-processing using MPI, the load distribution process occurs on each slave, from loading the image to cutting the image to get the features carried out in parallel. The resulting features are combined with the master for linear regression. In the use of CPU and Hybrid without the addition of MPI there is a difference of 2 minutes. Meanwhile, in the usage between CPU MPI and GPU MPI there is a difference of 1 minute. This demonstrates that implementing accelerated and parallel communications can streamline the processing of data sets and save computational costs. In this case, the use of MPI and GPU positively influences the proposed system.