Article Per Year (5 Year)
p-Index From 2020 - 2025
1.325
P-Index
This Author published in this journals
All Journal Jurnal Edukasi dan Penelitian Informatika (JEPIN) JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Jurnal Mantik Jurnal Computer Science and Information Technology (CoSciTech) INFOSYS (INFORMATION SYSTEM) JOURNAL Jurnal PkM (Pengabdian kepada Masyarakat)
Fitri Handayani
Universitas Muhammadiyah Riau
Arts Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Languange, Linguistic, Communication & Media Social Sciences

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Komparasi Support Vector Machine, Logistic Regression Dan Artificial Neural Network Dalam Prediksi Penyakit Jantung Handayani, Fitri
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 7, No 3 (2021): Volume 7 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v7i3.48053

Abstract

Penyakit jantung adalah salah satu penyakit yang menyebabkan resiko kematian cukup tinggi di dunia. Kolesterol, diabetes, tekanan darah tinggi merupakan faktor-faktor pemicu terjadinya penyakit jantung. Perlu deteksi sejak ini mengenai prediksi penyakit jantung pada setiap individu agar pencegahan dan pengobatan dapat segera dilakukan demi tingkat Kesehatan yang lebih baik. Berbagai metode dapat dilakukan untuk melakukan deteksi penyakit jantung, baik dengan metode tradisional dan metode yang memanfaatkan teknologi. Saat ini mulai banyak bermunculan system pendeteksi penyakit jantung dengan memanfaatkan algoritma machine learning. Algoritma machine learning dianggap mudah untuk diaplikasikan untuk mengklasifikasikan apakah seseorang terkena penyakit jantung. Penelitian ini mencoba melakukan klasifikasi penyakit jantung menggunakan dataset public dari UCI menggunakan tiga algorima machine learning, yaitu Support Vector Machine (SVM), Logistic Regression (LR) dan Artifiacial Neural Network (ANN). Ketiga algorima tersebut diuji menggunakan empat skenario pembagian data training dan testing yang berbeda, yaitu 90:10, 80:20, 70:40 dan 60:40. Dari hasil eksperimen didapatkan hasil akurasi tertinggi pada metode Logistic Regression sebesar 86% menggunakan skenario pembagian data 80:20.
Analisis Multi Kriteria Analisis Multi Kriteria Menggunakan Multi Attribute Utility Theory Dalam Seleksi Penerima Beasiswa Fitri Handayani
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 9 No 1 (2022): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v9i1.1531

Abstract

Abstract Politeknik Kampar is a vocational college in Kampar Regency, Riau Province. Determination of scholarship recipients at universities is still manual and takes a long time to make the right decisions. These problems can be analyzed using the Multi Attribute Utility Theory (MAUT) decision support system method so that the decision-making process can be carried out more quickly. Where the analysis of the MAUT method is suitable for many criteria. The assessment criteria used consisted of 10 criteria including parental income, home ownership status, housing conditions, number of dependents, parental status, report cards, academic achievements, non-academic achievements, extracurricular activities and organizational experience with a total of 50 datasets. The research process consists of scientific literature, problem identification, data collection, MAUT method analysis, ranking and drawing conclusions. The results of research using the MAUT method can help the scholarship recipient selection team with a fast, effective and objective process in the decision-making process.
Comparison of Simple Additive Weighting and Profile Matching Methods in Scholarship Recipient Selection Fitri Handayani
Jurnal Mantik Vol. 5 No. 3 (2021): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Private Universities organize scholarship programs that are given to prospective scholarship recipients with the aim of being able to help reduce the cost of education. So it is necessary to make the correct and targeted selection. However, the selection of scholarship recipients is still done manually. This can be done with accurate analysis. This study aims to determine the best algorithm of the two methods compared, namely Simple Additive Weighting and Profile Matching. The assessment criteria used consisted of parents' income, home owner status, parents' home condition, number of dependents and parental status. The results of the study using the Profile Matching method produced an accuracy of 100% while the Simple Additive Weighting method produced an accuracy of 96%.
Optimasi Metode K-Means dan K-Medoids Berdasarkan Jumlah Cluster dan Nilai DBI Dalam Pengelompokkan Produksi Kelapa Sawit Di Provinsi Riau Fina Nasari; Dahriani Hakim Tanjung; Fitri Handayani
INFOSYS (INFORMATION SYSTEM) JOURNAL Vol 7, No 2 (2023): InfoSys Februari 2023
Publisher : Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/infosys.7.2.2023.129-141

Abstract

Kelapa sawit merupakan salah satu jenis sumber daya alam yang terkenal didunia. Perkebunan kelapa sawit terbesar didunia berada di Indonesia. Provinsi  riau menjadi salah satu provinsi dengan produksi kelapa sawit tertinggi di Indonesia dengan luas kebun 2.8 juta Ha produksi 8.8 juta ton per tahun. Penyebaran kelapa sawit di provinsi riau hampir diseluruh kabupaten, sehingga perlu adanya pengelompokkan daerah produksi kelapa sawit. Clustering menjadi salah satu metode yang dapat  mengelompokkan data pada data yang sejenis. Proses clustering dapat menggunakan metode K-means atau K-medoids. Perlu adanya pengujian untuk melihat metode yang lebih optimal dalam proses cluster berdasarkan jumlah cluster dan nilai DBI untuk mendappatkan hasil pengelompokkan daerah produksi kelapa sawit terbaik. Pengujian menggunakan Tools Rapit Miner. Jumlah Cluster yang digunakan dalam pengujian ini adalah 2, 3 dan 5. Hasil penelitian ini menunjukkan Jumlah Cluster 2 menjadi cluster terbaik dengan nilai DBI untuk metode K-medoid -159796492242,667 dan metode K-Means -82338884292,014. Metode K-Medoid menjadi metode cluster terbaik dengan cluster yang dihasilkan berupa 7 kabupaten pada kelompok jumlah produksi Tinggi dan 5 kabupaten masuk pada kelompok jumlah produksi Rendah.
Pembudidayaan Jamur Merang Menggunakan Media Janjangan Kosong Kelapa Sawit di Desa Bukit Lingkar Handayani, Fitri; Mukhtar, Harun; Prastiwi, Adila Pramudiah; Suryanti, Anggi Aprilia; Fitriani, Aisyah; Chan, Ridzky; Rahmawilda, Rahmawilda; Munanda, Rizka; Aldi, M Tri; Fatma, Yulia; Hayami, Regiolina; Putra, Eka; Taufiq, Reny Medikawati; Firdaus, Rahmad
Jurnal PKM: Pengabdian Kepada Masyarakat Vol 7, No 4 (2024): Jurnal PkM: Pengabdian kepada Masyarakat
Publisher : Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/jurnalpkm.v7i4.23516

Abstract

Komparasi Algoritma Menggunakan Teknik Smote Dalam Melakukan Klasifikasi Penyakit Stroke Otak Fitri Handayani; Reny Medikawati Taufiq
Computer Science and Information Technology Vol 5 No 2 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v5i2.7439

Abstract

Stroke is a deadly disease. This can occur due to disturbances in brain function that occur suddenly, progressively and quickly. However, it is difficult to know the early symptoms of stroke. The application of data mining knowledge can be used to diagnose disease. This research was conducted to implement data mining in classifying brain stroke. The dataset used was obtained from Kaggle, totaling 4891 data. However, the dataset does not have a balanced amount of data for each class. To balance the data, the SMOTE technique is used which aims to increase accuracy. The application of the classification algorithms used, namely the Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) algorithms aims to determine the best algorithm performance. This research resulted in a comparison of the four algorithms which showed that the LR, RF and SVM algorithms produced the highest accuracy, precision, recall and f1-score values, namely 95% accuracy, 95% precision, 100% recall and 97% f1-score. The KNN algorithm produces lower accuracy, precision, recall and f1-score values, namely 90% accuracy, 95% precision, 85% recall and 90% f1-score.
Analisis Convolutional Neural Network LeNet-5 Dalam Klasifikasi Daun Mangga Fitri Handayani; Andi Sunyoto; Bayu Anugerah Putra
Computer Science and Information Technology Vol 5 No 3 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Mango is one of the agricultural productions. Like other agricultural crops, diseased mango leaves are a production problem. As a result, agricultural productivity decreases. This research aims to classify healthy or diseased mango leaves by developing a Convolutional Neural Network (CNN) based system with LeNet-5 feature extraction. The dataset used is sourced from Mendeley consisting of healthy leaf types totaling 265 images and diseased totaling 170 images. The data division used consists of 80% training data and 20% test data. The augmentation process is carried out to reduce over fitting. The results showed that the epoch process stopped at the 20th epoch and resulted in 93% accuracy. This shows that the CNN method for image classification can produce accurate accuracy in solving real-world problems.
Co-Authors Aldi, M Tri Andi Sunyoto Bayu Anugerah Putra Chan, Ridzky Dahriani Hakim Tanjung Eka Putra Fatma, Yulia Fina Nasari Fitriani, Aisyah Harun Mukhtar Hayami, Regiolina Munanda, Rizka Prastiwi, Adila Pramudiah Rahmad Firdaus Rahmawilda, Rahmawilda Suryanti, Anggi Aprilia Taufiq, Reny Medikawati