Claim Missing Document
Check
Articles

Found 22 Documents
Search

Effect of Modified Kimpul Flour Substitution and Glycerol Monostearate Concentration on The Physicochemical and Sensory Properties of Sweet Bread Setianingsih, Siti Nurlaela; Ujianti, Rizky Muliani Dwi; Muflihati, Iffah; Nurdyansyah, Fafa; Novita, Mega; Paramita, Diva Julia; Nofitasari, Shindi; Anggarini, Dola Mareta; Annajah, Abdillah Fathan Generus
Biology, Medicine, & Natural Product Chemistry Vol 14, No 2 (2025)
Publisher : Sunan Kalijaga State Islamic University & Society for Indonesian Biodiversity

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/biomedich.2025.142.679-683

Abstract

Wheat flour is the primary ingredient in sweet bread production, yet its import-dependent supply in countries like Indonesia prompts the need for alternative local ingredients. Kimpul tuber (Xanthosoma sagittifolium), rich in carbohydrates, presents a promising substitute, though its native starch properties are less suitable for baking. This study aimed to evaluate the effect of substituting wheat flour with heat moisture treatment (HMT)-modified kimpul flour and the addition of glycerol monostearate (GMS) on the physicochemical and sensory properties of sweet bread. A factorial completely randomized design was applied using three wheat-to-kimpul flour ratios (3:1, 1:1, and 1:3) and three GMS concentrations (2%, 3%, and 4%). Results showed that higher kimpul flour substitution increased moisture and carbohydrate content but reduced protein and fat levels. Textural properties such as hardness and adhesiveness also increased with kimpul content, but these were mitigated by the addition of GMS, particularly at 3%. The optimal formulation 1:1 wheat-to-kimpul ratio with 3% GMS produced sweet bread with the best overall sensory acceptance. The findings suggest that HMT-modified kimpul flour combined with GMS can serve as a functional and acceptable alternative to wheat flour in bread production. This supports food diversification strategies and promotes the utilization of local tuber-based flours in bakery applications.
Peningkatan Performa Prediksi Survival Pasien Gagal Jantung Menggunakan Stacking Ensemble Learning Salwa, Faiza Rulla; Novita, Mega; Renaldy, Ramadhan
JURNAL INFORMATIKA DAN KOMPUTER Vol 9, No 3 (2025): Oktober 2025
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v9i3.2126

Abstract

Prediksi kelangsungan hidup pasien gagal jantung merupakan aspek penting dalam mendukung pengambilan keputusan medis secara dini dan tepat. Penelitian ini bertujuan untuk meningkatkan akurasi prediksi kelangsungan hidup pasien gagal jantung dengan menerapkan metode Stacking Ensemble Learning yang menggabungkan tiga base learners, yaitu Decision Tree, Naive Bayes, dan K-Nearest Neighbor, serta menggunakan Support Vector Machine sebagai meta-learner. Dataset yang digunakan adalah Heart Failure Clinical Records dari UCI Machine Learning Repository yang telah melalui proses pra-pemrosesan berupa standardisasi numerik dan pembagian data menggunakan stratified sampling dengan rasio 80:20. Eksperimen dilakukan menggunakan validasi silang (5-fold cross-validation) dan tuning hyperparameter pada meta-learner menggunakan GridSearchCV untuk menemukan kombinasi terbaik dari parameter C dan gamma. Hasil evaluasi menunjukkan bahwa model stacking mampu mencapai akurasi sebesar 98,7% dan F1-score 0,9791, mengungguli semua model tunggal. Keberhasilan ini menunjukkan bahwa strategi penggabungan beberapa model ringan mampu meningkatkan kinerja sistem prediktif secara signifikan, tanpa menambah kompleksitas yang berlebihan. Oleh karena itu, pendekatan ini sangat potensial untuk diterapkan pada sistem pendukung keputusan klinis berbasis data, khususnya dalam konteks prediksi penyakit kronis.