Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal J-SIGN (Journal Of Informatics, Information System, And Artificial Intelligence) JoDENS: Journal of Digital Ecosystem for Natural Sustainability
Pangestu, Amora Antonio
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Perbandingan Performa Arsitektur Machine Learning untuk Deteksi Dini Depresi Berbasis Natural Language Processing dalam Bahasa Indonesia Pangestu, Amora Antonio; Purnajaya, Akhmad Rezki
J-SIGN (Journal of Informatics, Information System, and Artificial Intelligence) Vol 3, No 2 (2025): November
Publisher : Department of Informatics, Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/j-sign.v3i2.49873

Abstract

Depresi telah menjadi krisis kesehatan mental global yang mendesak. Pemanfaatan Natural Language Processing (NLP) pada analisis teks digital menawarkan potensi besar untuk deteksi dini depresi secara non-intrusif. Penelitian ini menyajikan analisis komparatif dari tiga arsitektur machine learning, yaitu Naive Bayes, Long Short-Term Memory (LSTM), dan Convolutional Neural Network (CNN) untuk mengklasifikasikan teks berbahasa Indonesia. Metodologi penelitian dimulai dengan akuisisi dan pra-pemrosesan (pembersihan, case folding, tokenisasi, stopword removal) dataset 10.801 teks yang teranotasi psikolog. Model dilatih pada 75% data dan dievaluasi pada 25% data uji menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil menunjukkan bahwa arsitektur CNN mencapai performa tertinggi dengan F1-score seragam sebesar 94%. Kinerja ini sedikit melampaui model LSTM (93%) dan secara signifikan mengungguli Naive Bayes (86%). Keterbatasan penelitian ini mencakup fokus pada klasifikasi biner dan belum digunakannya arsitektur Transformer. Temuan ini memberikan landasan penting untuk pengembangan deteksi kesehatan mental di Indonesia yang lebih akurat, adaptif, efektif, dan relevan terhadap konteks budaya lokal.
PREDIKSI VOLUME PENJUALAN GAS PT PGN (PERSERO) MENGGUNAKAN REGRESI LINEAR BERGANDA Edison; David; Pangestu, Amora Antonio; Efanly; Rindiany
Journal of Digital Ecosystem for Natural Sustainability Vol 1 No 1 (2021): Juli 2021
Publisher : Fakultas Komputer - Universitas Universal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63643/jodens.v1i1.23

Abstract

PT PGN (Persero) gets an erratic gas sales volume every year, this can affect the existing gas supply. If the existing gas supply can't fulfill the demand or vice versa, the existing supply becomes excessive and affect company performance. Of these problems, it is necessary to predict sales volume to determine future inventory. This research uses Multiple Linear Regression Algorithm by applying the Cross-Industry Standard Process for Data Mining (CRISP-DM) method. The Multiple Linear Regression Algorithm aims to find the value of the regression equation, after getting the regression equation, the next step is to do it. Error analysis to determine the accuracy of predictions using MAD, MSE, and MAPE through R.Studio software. From the processing results, the results obtained from the sales volume in 2016 amounted to 109 443.97, 2017 amounted to 79 521.42, 2018 amounted to 102 059.01 and in 2019 amounted to 86 799.89 at PT.PGN (Persero). Then with the resulting error analysis, the MAD value is 27741.58, the MSE value is 791516224.16 and the MAPE value is 27.18%.
Co-Authors david Edison Efanly Purnajaya, Akhmad Rezki Rindiany