Review Jurnal Artificial neural network based particle swarm optimization in predictions mortality rate of broiler chicken

Review jurnal ini dibuat untuk memenuhi tugas UAS mata kuliah Data Mining atas nama Siti Atisa Hartati (20190050027)

Judul Jurnal :

Artificial neural network based particle swarm optimization in predictions mortality rate of broiler chicken

Link Jurnal :

https://iopscience.iop.org/article/10.1088/1755-1315/335/1/012007/pdf

Review :

Success in broiler farms can be assessed from the mortality rate of chickens and also a solution to reduce the mortality rate of chickens. But in the process there are obstacles that is the death of chickens that tend to fluctuate so that of course resulted in financial losses for farmers. to prevent it required a method that can predict and control the mortality rate of broiler chickens. in this research, data mining method used is artificial neutral network (ANN) based on particle swarm optimization (PSO), to produce accurate prediction with excellent iteration and also small error rate. The result of analysis in predicting mortality rate of broiler chickens by artificial neutral network method in combination with particle swarm optimization get better RMSE result (0.135) than artificial neutral network have not been optimized (.381) with january mortality data and result of application quisioner made value 83, 125 which can be categorized well and enough help the farmer in controlling prediction of chickens mortality rate broiler.

1. apa urgensinya sehingga harus ada penelitian itu?

Jawab : artificial neutral network, mortality rate, particle swarm optimization.

2. Bagaimana proses metodologi penelitian yang ditempuh?

In this research used two methods that support each other is particle swarm optimization neutral network.

    a. step one with artificial neutral network

    b. step two with particle swarm optimization

    c. step three software testing with SQA

3. Bagaimana proses ANN dalam memberikan solusi dari permasalahan yang ada?

    a. Dataset. the dataset used for this study is data on the death of broiler chickens PT. Jafpa Comfeed Indonesia Tbk unit Kalapanunggal 2 from 2014 to 2017. the analysis process that predict the mortality of broiler chickens for 2018 using the average data from 2014 to 2017 is reduced by 10% and the prediction for 2019 using 208 data minus 10% in accordance with request from management.

    b. ANN model. ANN model used is a backpropagation model which means a method that minimizes errors in output generated by the network. in figure 3 below is the input unit setting, hidden layer and output on backpropagation. The hidden layer is used as much as 2 hidden layers. Input data is monthly data from chickens mortality data for the period 2014 to 2017 while the output unit is prediction data.

    c. PSO-based neural network, the configuration for the artificial neural network method is based on particle swarm optimization (PSO).

    d. Comparison between ANN an PSO-based ANN. the RMSE result obtained from this study using artificial neural network and artificial neural network with PSO.

    e. Prediction result data.

    f. Implementation of the system. there are two diagrams presented use case diagram and class diagram.

    g. Interface created.

4. Apa saran anda dalam penelitian tersebut?

Swarm of artificial neural network based particles optimization in predicting broiler mortality chicken. Of course, this research is expected to be able to reduce the mortality rate of broilers by being able to predict accurately.