Claim Missing Document
Check
Articles

Found 22 Documents
Search

Kajian Model Jaringan Syaraf Tiruan Untuk Memprediksi Secara Dini Tingkat Kelulusan Mahasiswa Tatang Rohana; Euis Nurlaelasari; Elsa Elvira Awal; Hilda Yulia Novita
Technologia : Jurnal Ilmiah Vol 15 No 4 (2024): Technologia (Oktober)
Publisher : Fakultas Teknologi Informasi, Universitas Islam Kalimantan Muhammad Arsyad Al Banjari, di bawah koordinasi UPT Publikasi dan Pengelolaan Jurnal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/tji.v15i4.15583

Abstract

ABSTRAKMasalah: Penelitian ini terkait dengan kajian algoritma jaringan syaraf tiruan untuk memprediksi secara dini tingkat kelulusan mahasiswa. Tujuan: Tujuan penelitian untuk mendeteksi atau memprediksi tingkat kelulusan mahasiswa yang lulus  tepat waktu, sehingga hasilnya diharapkan bisa memberikan kontribusi bagi progam studi dalam menganalisa tingkat kelulusan mahasiswa.Metode: Algoritma yang dipakai meliputi Multilayer Perceptron, Support Vector Machine, dan Decision Tree. Kemudian akan dibandingkan algoritma mana yang memiliki tingkat akurasi yang terbaik dalam memprediksi tingkat kelulusan mahasiswa.Hasil: Berdasarkan hasil penelitian, model Decision Tree memiliki tingkat error rate yang paling baik yaitu 0, model Support Vector Machine sebesar 0.011, dan Multilayer Perceptron 0.029. Berdasarkan  hasil uji performansi dengan Confusion Matrix, model Multilayer Perceptron  memiliki akurasi sebesar 97,1%, Support Vector  Machine 98,9%, dan Decision Tree memiliki akurasi 100%.Kesimpulan: Model Decision Tree memiliki tingkat akurasi terbaik, sehingga algoritma tersebut bisa digunakan dalam membuat sistem  prediksi kelulusan mahasiswa tepat waktu. Untuk penelitian selanjutnya, disarankan untuk menambahkan lebih banyak data mahasiswa agar hasil penelitian bisa lebih baik. Variabel data set juga bisa diperluas tidak hanya dari aspek akademik mahasiswa, tetapi juga dari aspek non-akademik dan latar belakang ekonomi keluarga, seperti pendapatan orang tua, status pekerjaan mahasiswa, dan variabel lainnya.Kata kunci: Jaringan Syaraf, Prediksi, Multilayer Perceptron, Support Vector Machine, Decision Tree  
Comparison Model Optimal Machine Learning Model With Feature Extraction for Heart Attack Disease Classification Salsa Desmalia; Amril Mutoi Siregar; Kiki Ahmad Baihaqi; Tatang Rohana
Scientific Journal of Informatics Vol. 11 No. 2: Regular Issue
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.4561

Abstract

Purpose: The purpose of this study is to classify the number of people affected by heart disease and those not affected by heart disease based on various categories of heart attack causes. This study aims to urge people to take better care of their health and to serve as a reference for doctors to educate patients about the dangers of heart attacks. Methods: The model will be constructed via a machine learning methodology. The algorithms utilized in its development encompass the Support Vector Machine (SVM) algorithm, the K-Nearest Neighbor (k-NN) algorithm, and the Random Forest (RF) algorithm.  This study utilizes principal component analysis (PCA) as a means of extracting optimized features from the dataset, employing techniques for dimension reduction prior to modeling the data. Result: Cumulative explication of the concept of variance constitutes a foundational aspect of PCA (principal component analysis) within the scope of the current research, namely a dimensionality reduction technique employed in multivariate data analysis to facilitate model development, thereby enabling the creation of more optimal and comprehensive models. In this research, the dimensions of training data are incorporated during the process of model creation.   The results show KNN model exhibits the highest performance, with an accuracy of 86%, precision of 86%, recall of 91%, and F1-score of 88%. Furthermore, evaluation using the ROC metric also provides a relatively favorable value, 0.85. Novelty: Researchers used 1190 patient data sourced from Kaggle. Before modeling the algorithm, researchers conducted EDA & Preprocessing which includes missing values to find data that does not have information, then duplicate data to find duplicated data, there are 270 duplicated data, then the duplicated data is deleted so that the data becomes 737, then PCA implementation is carried out.  PCA is reducing features automatically without changing the data.