Article Per Year (5 Year)
p-Index From 2021 - 2026
2.155
P-Index
This Author published in this journals
All Journal Jurnal Informatika Jurnal Informatika dan Teknik Elektro Terapan Proceeding of the Electrical Engineering Computer Science and Informatics Jurnal Teknologi dan Sistem Komputer Informatika Mulawarman: Jurnal Ilmiah Ilmu Komputer JURNAL REKAYASA TEKNOLOGI INFORMASI ILKOM Jurnal Ilmiah METIK JURNAL Sains, Aplikasi, Komputasi dan Teknologi Informasi TEPIAN Indonesian Journal of Informatic Research and Software Engineering Adopsi Teknologi dan Sistem Informasi Information Technology Education Journal Journal of Data Mining and Information Systems
Widians, Joan Angelina
Program Studi Teknik Informatika, Universitas Mulawarman
Aerospace Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Engineering

Published : 26 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 26 Documents
Search

 1   2   3 
Penerapan Certainty Factor dalam Sistem Pakar Penyakit Tanaman Andi Tejawati; Joan Angelina Widians; Andi Azza Az-Zahra; Edy Budiman
Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer Vol 17, No 1 (2022): Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer
Publisher : Mulawarman University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jim.v17i1.7521

Abstract

Perkembangan teknologi informasi telah mencakup segala bidang kehidupan, termasuk bidang pertanian. Salah satu bidang pertanian yang sedang dikembangkan ialah pertanian lada (Piper ningrum L). Dalam perkembangannya tanaman lada dapat terjangkit penyakit yang akan berpengaruh pada hasil panen yang akan diterima oleh petani. Penelitian ini mengembangkan suatu sistem pakar penyakit yang menyerang tanaman lada dengan metode Certainty Factor dan menggunakan penelusuran inferensi Forward Chaining. Sistem pakar merupakan bagian dari kecerdasan buatan, dimana sistem mengadopsi pengetahuan manusia yang ahli ke dalam komputer untuk menyelesaikan suatu pekerjaan yang biasanya memerlukan kepakaran seseorang. Penelitian ini dilakukan di UPTD Pengembangan Perlindungan Tanaman Perkebunan Provinsi Kalimantan Timur. Terdapat enam penyakit yang menyerang tanaman lada yaitu penyakit busuk pangkal, penyakit kuning, penyakit keriting daun, penyakit jamur pirang, penyakit karat merah dan penyakit bercak daun Colletotrichum. Pada implementasi sistem dilakukan pengujian dengan memilih beberapa gejala yang menyerang tanaman lada antara lain daun berubah warna, terdapat bercak pada daun, daun menguning, pangkal batang berubah warna, akar mengalami pembusukan, pangkal batang berwarna coklat, dan akar berwarna hitam. Berdasarkan gejala yang dipilih pengguna tersebut, diperoleh hasil berupa identifikasi penyakit busuk pangkal batang dengan nilai Certainty Factor sebesar 88.57% yang berarti bahwa tanaman lada tersebut hampir pasti terkena penyakit busuk pangkal batang.
Komparasi Algoritma K-Means dan DBSCAN dalam Klasterisasi Indeks Pembangunan Gender Tingkat Kabupaten/Kota di Indonesia: Comparison of K-Means and DBSCAN Algorithms in Clustering Indonesia's Regional Gender Development Index Sifwah Fatin Sofwani; Muhammad Riva Fachrodhiya; Masna Wati; Joan Angelina Widians
Indonesian Journal of Informatic Research and Software Engineering (IJIRSE) Vol. 6 No. 1 (2026): Indonesian Journal of Informatic Research and Software Engineering (IJIRSE)
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/ijirse.v6i1.2838

Abstract

Analisis terhadap ketimpangan pencapaian pembangunan antara laki-laki dan perempuan memerlukan pendekatan pemodelan data tingkat lanjut dalam pemetaan distribusi spasial secara akurat. Penelitian ini mengeksplorasi masalah disparitas pembangunan gender di tingkat kabupaten/kota di Indonesia menggunakan data tahun 2025 yang diakses dari BPS pada Mei 2026 dengan melakukan studi perbandingan antara dua algoritma yaitu K-Means dan Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Pemecahan masalah difokuskan pada pengelompokkan 514 wilayah administratif di Indonesia menggunakan indikator pembentuk Indeks Pembangunan Manusia (IPM) berbasis gender, yang meliputi Angka Harapan Lama Sekolah, Rata-rata Lama Sekolah, Pengeluaran per Kapita yang Disesuaikan, dan Umur Harapan Hidup saat lahir. Metodologi yang digunakan dalam penelitian ini yaitu preprocessing data, kalkulasi indeks komposit menggunakan rata-rata geometrik sesuai standar Badan Pusat Statistik terbaru, serta menguji bagaimana struktur algoritma tersebut diatur dalam mengolah data. Pengujian menggunakan Silhouette Score dan Davies-Bouldin Index menunjukkan bahwa algoritma K-Means secara keseluruhan lebih unggul dalam menghasilkan klaster yang kompak dan terstruktur untuk kategorisasi umum wilayah berbasis capaian IPG. Algoritma DBSCAN berperan sebagai pelengkap yang efektif dalam mengidentifikasi 33 kabupaten/kota sebagai anomali dengan profil pembangunan gender yang menyimpang secara signifikan dari pola umum. Penelitian ini merekomendasikan K-Means sebagai algoritma utama klasterisasi wilayah IPG, dengan DBSCAN sebagai instrumen pendukung untuk deteksi daerah prioritas intervensi kebijakan gender secara khusus
ANALISIS EXPLAINABLE AI PADA PERBANDINGAN MODEL XGBOOST DAN LOGISTIC REGRESSION UNTUK CREDIT SCORING Ari Fullah; Fathir Januarta; Vashih Al Farizi Farizi; Muhammad Nashrul Fakhri; Anindita Septiarini; Joan Angelina Widians; Akhmad Irsyad
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 3 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i3.9842

Abstract

Perkembangan machine learning dalam industri keuangan mendorong penggunaan model prediktif yang semakin kompleks untuk penilaian risiko kredit. Meskipun model seperti XGBoost menawarkan akurasi tinggi, tantangan utama yang muncul adalah kurangnya transparansi dalam pengambilan keputusan. Penelitian ini bertujuan membandingkan performa model XGBoost dan Logistic Regression dalam prediksi credit scoring, serta menganalisis interpretabilitas kedua model menggunakan metode SHAP (SHapley Additive exPlanations). Data yang digunakan adalah Credit Risk Dataset dari platform Kaggle yang terdiri atas 32.581 observasi dengan 11 variabel independen dan 1 variabel target. Tahapan penelitian meliputi preprocessing data, pemodelan, evaluasi, dan analisis SHAP. Hasil evaluasi menunjukkan XGBoost mengungguli Logistic Regression dengan Accuracy 0,9122 berbanding 0,8104, F1-Score 0,7956 berbanding 0,6356, dan ROC AUC 0,9458 berbanding 0,8635. Analisis SHAP mengungkap bahwa loan_percent_income dan loan_int_rate merupakan fitur paling berpengaruh pada kedua model, konsisten dengan konsep Debt-to-Income Ratio dalam analisis kredit konvensional. Meskipun XGBoost unggul secara prediktif, SHAP terbukti mampu menjelaskan mekanisme keputusan kedua model secara transparan. Penelitian ini menunjukkan bahwa kombinasi XGBoost dan SHAP merupakan pendekatan yang direkomendasikan untuk pengembangan sistem credit scoring yang akurat sekaligus dapat dipertanggungjawabkan.
Food Delivery Time Prediction using Tree-Based Ensemble Models: A Comparative Study with Explainable Artificial Intelligence Raihanfitri Adi Kalipaksi; Haviluddin Haviluddin; Anindita Septiarini; Joan Angelina Widians; Novianti Puspitasari
Information Technology Education Journal Vol. 5, No. 3, August (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i3.12157

Abstract

Purpose – Being able to predict delivery time accurately is important for online food delivery services, both for operational efficiency and customer satisfaction. However, this is not an easy task. Delivery time depends on many factors that are related to each other, such as courier characteristics, delivery distance, and order-related information, and these factors interact in complex ways. This study looks at how well tree-based ensemble learning models can predict food delivery time, and also uses explainable artificial intelligence so the models can still be interpreted properly. Design – This study uses 45,593 delivery records taken from Kaggle. In this study, four tree-based ensemble models were developed, namely Random Forest, Gradient Boosting, XGBoost, and LightGBM, with each model optimized through hyperparameter tuning. The models were evaluated using repeated 5-fold cross-validation with three repetitions, and their performance was assessed using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R². Findings – LightGBM Tuned came out with the best numerical performance, showing an MAE of 5.678 minutes, RMSE of 7.204 minutes, and R² of 0.411. However, based on ANOVA and Tukey's post-hoc test, the difference in performance between the best boosting-based models was not statistically significant. SHAP analysis also showed that courier rating, delivery distance, courier age, and several interaction features were the factors that had the biggest influence on delivery time prediction. Research implications – The findings suggest that boosting-based ensemble learning models can provide moderate predictive performance while offering interpretable insights into the factors contributing to delivery time predictions. Nevertheless, the moderate R² value indicates that additional operational variables, such as traffic conditions, restaurant preparation time, and courier workload, may be required to improve practical prediction reliability. Originality/value – This study combines ensemble learning, feature engineering, statistical validation, and explainable artificial intelligence together to evaluate both the predictive performance and interpretability of models for food delivery time prediction. 
Analisis Perbandingan Metode K-Means dan DBSCAN dalam Pengelompokan Provinsi Di Indonesia Berdasarkan Kasus Penyakit Wahyu Aditya; Razib Ramadhan; Masna Wati; Joan Angelina Widians
JDMIS: Journal of Data Mining and Information Systems Vol. 4 No. 2 (2026): August 2026
Publisher : Yayasan Pendidikan Penelitian Pengabdian Algero

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54259/jdmis.v4i2.7676

Abstract

This study compares the performance of K-Means and DBSCAN algorithms in clustering 38 Indonesian provinces based on six infectious disease indicators in 2025, namely Tuberculosis (TB), HIV/AIDS, leprosy, malaria, and Dengue Hemorrhagic Fever (DHF). The uneven distribution of diseases across regions requires accurate mapping for targeted public health interventions. The research stages included handling missing values with median imputation, Z-Score normalization, clustering modeling, and evaluation using Silhouette Score, Davies-Bouldin Index (DBI), and Calinski-Harabasz Index (CHI) metrics. Evaluation results indicate that the DBSCAN algorithm (eps=1.2, MinPts=2) consistently outperformed K-Means (K=6) across all three parameters. DBSCAN achieved a Silhouette Score of 0.6282, DBI of 0.4059, and CHI of 21.8583, whereas K-Means only reached a Silhouette Score of 0.4395, DBI of 0.6349, and CHI of 15.8653. DBSCAN's superiority lies in its ability to isolate extreme outliers, such as malaria cases in Papua and DHF in Bali, as noise. In conclusion, DBSCAN is proven to be more robust and representative for clustering national-scale epidemiological data with right-skewed distributions. The resulting cluster map can be utilized by the government to prioritize specific and targeted health program allocations in each region.
Multivariate LSTM With the RSI-14 Technical Indicator for Stock Price Forecasting Muhammad Jahron; Joan Angelina Widians; Andi Tejawati
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3919

Abstract

Stock price forecasting is a key part of investment decision-making, especially for high-capitalization stocks such as PT Bank Central Asia Tbk. (BBCA). Accurate prediction remains challenging because complex market dynamics and nonlinear price movements influence stock prices. This study proposes a multivariate Long Short-Term Memory (LSTM) model that integrates the closing price and the RSI-14 technical indicator as input features to improve accuracy over conventional univariate approaches. We obtained historical data from the Yahoo Finance API covering January 2015 to December 2025, totaling 2,698 trading days after RSI-14 feature engineering. The dataset was split to 80:20 for training and testing, with MinMaxScaler normalization applied only to the training data to prevent data leakage. The LSTM model used 100 neurons with an input shape of (10, 2) and was trained using the Adam optimizer with early stopping at epoch 24 to avoid overfitting. Evaluation results show an RMSE of 169.72 IDR, an MAE of 134.68 IDR, a MAPE of 1.58%, and an R² of 0.9368, indicating a good regression-level fit. Adding the RSI-14 feature improved the regression metrics relative to a univariate closing-price-only LSTM. Given the modest trend-classification accuracy and the lack of trading back testing, transaction costs, or risk-adjusted performance measures, view the results as a methodological contribution rather than direct evidence of practical investment value. Future work could extend this research by exploring hybrid architectures that combine LSTM with attention mechanisms or Transformer-based models, and by validating the approach on other high-capitalization stocks to assess generalizability across market conditions.
Co-Authors Ahmad Adha Abdullah Aji Ayu Muvita Putri Alameka, Faza Andi Azza Az-Zahra Andi Maulana Anindita Septiarini, Anindita Anton Prafanto Arfa’ Yunida Nurhafizhah Ari Fullah Bambang Cahyono Budiman, Edy Erma Yuliani Farahdina Nur Rizkyani Farid Al Muhaimin Fathir Januarta Faza Alameka Faza Alameka Firdaus, Muhammad Haga Daffa Aska Firmanda Hairah, Ummul Hamdani Hamdani Haviluddin Haviluddin Herman Santoso Pakpahan Irsyad, Akhmad Islamiyah Islamiyah Maratus Soleha Muhammad Akbar Muhammad Bambang Firdaus Muhammad Firdaus Muhammad Jahron Muhammad Nashrul Fakhri Muhammad Riva Fachrodhiya Muhammad Sofian Sauri Nada Sadida Faza Noval Bayu Setiawan Puspitasari, Novianti Raihanfitri Adi Kalipaksi Razib Ramadhan Renol Sulle Risa Farrid Christianti Rozy Rivaldi Sifwah Fatin Sofwani Sukma Dewi Hardi Yanti Tejawati, Andi Umayatul Choerohnur Vashih Al Farizi Farizi Wahyu Aditya Wati, Masna Zainal Arifin