Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : journal of intelligent software systems

Classification of Cancer Based on RNA Data Using Elman Recurrent Neural Network Eka Alifia Kusnanti; Anisa Nur Azizah; Alven Safik Ritonga
Journal of Intelligent Software Systems Vol 5, No 1 (2026): July 2026
Publisher : LPPM UTDI (d.h STMIK AKAKOM) Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiss.v5i1.2754

Abstract

Cancer is one of the deadliest diseases whose number of sufferers continues to increaseevery year. The development of cancer cells can quickly spread to all parts of the bodythrough the bloodstream or from the lymphatic system so that it can cause death. Thiscan happen because there is a disorder that exists in the gene. The basic thing in geneticsis the monitoring of gene expression itself, namely by measuring from mRNA not fromprotein because the sequence of mRNA will hybridize with complementary DNA and RNA.The purpose of this study is to classify cancer based on RNA data using the ElmanRecurrent Neural Network method. In the recurrent network there are two inputs, namelythe actual input and the contextual input. The iteration process is much faster due tofeedback, so parameter updates and convergence are also faster. The data used are RNAdata with four classes, namely BRCA or breast adenocarcinoma (breast cancer), KIRC orkidney renal clear cell carcinoma (kidney cancer), UCEC or uterine corpus endometrialcarcinoma (uterine cancer), and LUAD or lung adenocarcinoma (lung cancer). The datawill be preprocessed using a minmax scaler then classified using ERNN with trials ofdata sharing, learning rate, and the number of hidden layers. The best combinationof parameters was obtained at 20 nodes hidden layer I, 50 nodes hidden layer II, andlearning rate 0.1. In this model, the accuracy reached 99.19 %, sensitivity of 99.03 %and specificity of 99.72 %. The time required for the model is 19 seconds.