Claim Missing Document
Check
Articles

Found 12 Documents
Search

Perbandingan Algoritma Machine Learning Untuk Mendeteksi Gagal Jantung Berbasis Seleksi Fitur Rfecv Dan Penyeimbangan Data Smote Setyawan, Ari; Sulistianingsih, Neny; Rismayati, Ria
CORISINDO 2025 Vol. 1 (2025): Prosiding Seminar Nasional CORISINDO 2025
Publisher : CORISINDO 2025

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/corisindo.v1.5605

Abstract

Deteksi dini gagal jantung merupakan tantangan signifikan dalam dunia medis karena kompleksitas faktor risikonya. Penelitian ini bertujuan membandingkan kinerja enam algoritma machine learning dalam memprediksi risiko gagal jantung dengan pendekatan CRISP-DM. Data klinis sebanyak 299 pasien diproses melalui seleksi fitur menggunakan Recursive Feature Elimination with Cross-validation (RFECV) serta penyeimbangan kelas dengan Synthetic Minority Over-sampling Technique (SMOTE). Algoritma yang dievaluasi meliputi Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, Random Forest, dan Gradient Boosting. Evaluasi dilakukan menggunakan validasi silang berstrata dengan metrik akurasi, presisi, recall, dan F1-score. Hasil menunjukkan Random Forest mencapai performa terbaik dengan akurasi dan F1-score sebesar 91,20%, diikuti Gradient Boosting dengan 90,20%. Implementasi SMOTE terbukti meningkatkan kemampuan model, terutama dalam mendeteksi kelas minoritas. Temuan ini menegaskan bahwa metode ensemble seperti Random Forest, dikombinasikan dengan RFECV dan SMOTE, efektif untuk klasifikasi risiko gagal jantung secara akurat dan andal.
Inventarisasi Keanekaragaman Flora sebagai Upaya Konservasi di Kawasan PLTA Way Besai, Lampung Barat Munawaroh, Khoryfatul; Tohir, Rizki Kurnia; Anita, Vilda Puji Dini; Hasibuan, Mhd Muhajir; Tartil, Tafdhilah; Faedloni, Akbar Ash Shiddiqi; Setyawan, Ari; Azhaar, Daliilah Haniifah; Christoper, Ruben; Johanes, Ricky; Pandapotan, Sumitro; Aziz, Agung Abdul
Biocaster : Jurnal Kajian Biologi Vol. 6 No. 1 (2026): January
Publisher : Lembaga Pendidikan, Penelitian, dan Pengabdian Kamandanu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36312/biocaster.v6i1.704

Abstract

The Way Besai Hydroelectric Power Plant (PLTA) is located in West Lampung Regency, Lampung Province, with a capacity of 90.4 MW and utilizes water from the Way Besai River. The availability of stable water discharge is highly dependent on the vegetation conditions in the catchment area. This study aims to examine the diversity of flora and vegetation sustainability in the Way Besai hydropower plant area using an exploration method divided into six observation lines. The results showed that there were 57 types of plants belonging to 21 families. The most common species are sonokeling (Dalbergia latifolia) with 140 individuals and seripit (Crypteronia paniculata) with 113 individuals. The families with the highest number of species are obtained from the families Moraceae and Fabaceae. The types of the Moraceae family are dominated by Ficus spp., which acts as a source of animal feed, while from the Fabaceae family, there are more types of multipurpose plants (MPTS). The diversity of species and evenness of flora around the Way Besai hydropower plant is relatively high, as shown by the diversity index value (H') of 3.281 and the evenness index value (E) of 0.812. Although this value is relatively high, the maintenance and conservation of flora still needs to be carried out intensively to maintain the stability of the water discharge of the Way Besai River. These results confirm that the vegetation around the Way Besai hydropower plant is still relatively sustainable, but sustainable conservation efforts are needed to control land conversion that has the potential to reduce the water discharge of the Way Besai River.