Article Per Year (5 Year)
p-Index From 2021 - 2026
2.66
P-Index
This Author published in this journals
All Journal IT JOURNAL RESEARCH AND DEVELOPMENT Jusikom : Jurnal Sistem Komputer Musirawas JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI JURNAL TEKNOLOGI DAN OPEN SOURCE Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Building of Informatics, Technology and Science Zonasi: Jurnal Sistem Informasi Journal of Applied Data Sciences Mitra Mahajana: Jurnal Pengabdian Masyarakat Jurnal J-PEMAS Jurnal Algoritma SATIN - Sains dan Teknologi Informasi The Indonesian Journal of Computer Science
Edwar Ali
Tenik Informatika, STMIK Amik Riau
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Public Health Social Sciences

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
Sentimen Pengguna Aplikasi BRImo: Kinerja Algoritma Support Vector Machine, Naive Bayes, dan Adaboost Susandri; Yurnalis; Edwar Ali; Susanti; Asparizal
SATIN - Sains dan Teknologi Informasi Vol 9 No 2 (2023): SATIN - Sains dan Teknologi Informasi
Publisher : STMIK Amik Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33372/stn.v9i2.1057

Abstract

Dalam konteks perkembangan industri perbankan yang semakin maju, pemanfaatan teknologi modern menjadi faktor kunci untuk meningkatkan kualitas layanan dan memenangkan persaingan di era digital. Bank Rakyat Indonesia (BRI) memikat perhatian masyarakat melalui peluncuran aplikasi perbankan seluler, BRImo. Namun Bank ini perlu meraih pandangan dan pengalaman nasabah terhadap aplikasi mobile banking untuk meningkatkan kualitas pelayanan. Penelitian ini memiliki tujuan untuk menganalisis ulasan pengguna BRImo sebagai objek penelitian. Komparasi dilakukan antara algoritma Support Vector Machine (SVM), Naive Bayes (NB), dan Adaboost dalam mengolah data teks. Evaluasi dilakukan berdasarkan tingkat akurasi, presisi, recall, dan nilai F1-score. Hasil penelitian menunjukkan bahwa algoritma SVM memberikan kinerja terbaik dalam mengklasifikasikan tanggapan masyarakat terhadap aplikasi BRImo, dengan tingkat akurasi sebesar 90,4%, presisi 90,8%, recall 90%, dan nilai F1-score 90,3%. Sebagai perbandingan, algoritma Adaboost memberikan nilai terendah dengan tingkat akurasi sebesar 87%, presisi 87,2%, recall 86,8%, dan nilai F1-score 86,9%.
Perbandingan Kinerja Xgboost Dan Lightgbm Dalam Klasifikasi Depresi Pada Mahasiswa Berdasarkan Faktor Demografi Dan Akademik Pratama, Farhan; Ali, Edwar; Rahmaddeni; Agustin, Wirta
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2439

Abstract

Depresi merupakan salah satu gangguan mental yang umum dialami mahasiswa, sehingga berdampak signifikan terhadap kesejahteraan psikologis dan performa akademik mereka. faktor-faktor seperti jenis kelamin, usia, tekanan finansial, tekanan belajar, kepuasan studi, dan waktu belajar yang tidak proporsional diketahui berkontribusi dalam memengaruhi kondisi tersebut. penelitian ini bertujuan untuk membandingkan kinerja algoritma XGBoost dan LightGBM dalam mengklasifikasikan risiko depresi pada mahasiswa, serta mengembangkan model melalui teknik tuning parameter menggunakan RandomizedSearchCV untuk meningkatkan akurasi prediksi. dataset yang digunakan berasal dari platform Kaggle yang terdiri dari 502 baris data. evaluasi performa dilakukan menggunakan metrik akurasi, precision, recall, f1-score, dan AUC-ROC, pada skenario pembagian data 80:20 dan 70:30, baik dengan parameter default maupun setelah tuning. hasil penelitian menunjukkan bahwa model XGBoost dengan tuning pada pembagian data 80:20 memberikan performa terbaik dengan akurasi 82,18%, precision 85,11%, recall 78,43%, f1-score 81,63%, dan AUC-ROC sebesar 0,8973. terbaik kemudian diimplementasikan dalam bentuk aplikasi web menggunakan Streamlit, guna memberikan prediksi risiko depresi secara otomatis dan interaktif, sehingga memudahkan pengguna non-teknis dalam mendeteksi kondisi tersebut secara praktis.
Optimasi Klasifikasi Tingkat Obesitas Pada Remaja Berdasarkan Pola Hidup Menggunakan SVM Dengan Teknik Smote Setiawan, Andri; Yanti, Rini; Ali, Edwar; Yenni, Helda
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2509

Abstract

Obesity is a condition caused by an imbalance between energy intake and expenditure, characterized by excessive fat accumulation in the body. Obesity is influenced by four factors, namely genetics, economics, lack of activity, and diet. The purpose of this study is to analyze the effectiveness of the SMOTE method in improving the accuracy of classification in the Support Vector Machine method and to compare the accuracy of the Support Vector Machine method with the SMOTE and non-SMOTE techniques on adolescent obesity data. The dataset used was obtained from the Kaggle website, which contained 2,111 records. The model evaluation used a confusion matrix with accuracy, precision, recall, and F1-score measurements and used 80:20 data splitting. The results showed that the SVM model using Smote performed well with an accuracy of 88% for Linear SVM, 82% for RBF SVM, and 93% for Polynomial SVM, while the SVM model without Smote achieved an accuracy of 88% for Linear SVM, 79% for RBF SVM, and 91% for Polynomial SVM. The best classification model was then implemented into a Streamlit-based web application to facilitate the process of automatically predicting obesity levels, thereby helping to raise awareness of the potential risks of obesity.
Prediksi Dukungan Publik Terhadap Program Makan Bergizi Gratis (MBG) Menggunakan Analisis Sentimen Berbasis Long Short-Term Memory (LSTM) Novfuja, Elma; Efrizoni, Lusiana; Ali, Edwar; Susanti, Susanti
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2690

Abstract

The Free Nutritious Meal Program (MBG) is a public policy that requires evaluation based on public opinion. This study developed a Long Short-Term Memory (LSTM) model to classify public sentiment from 13,923 X reviews, collected using the tweet-harvest library. The data was processed with Word2Vec weighting and Lexicon-Based labeling, resulting in 73.4% positive sentiment and 26.6% negative sentiment. The model was tested with train-test split ratios of 60:40, 70:30, 80:20, and 90:10, with the best performance at a ratio of 80:20 (91.71% accuracy, 89% precision, 90% recall, 89% F1-score). The model architecture includes Embedding, LSTM (128 units), Dropout (70%), and Dense layers, optimized with categorical_crossentropy and Adam. The confusion matrix evaluation shows the effectiveness of the model, despite weak negative classes due to data imbalance. The results provide insights for improving MBG implementation, with LSTM excelling at capturing text patterns compared to SVM and BERT.
Mobile Application for Integrated Forest and Land Fire Reporting utilizing AI and Community Participation for Disaster Mitigation Ali, Edwar; Khairani Djahara; Rian Pradewanta
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.5064

Abstract

Forest and Land Fires in Indonesia represent a chronic disaster with multidimensional impacts, marked by economic losses reaching Rp. 72.8 trillion in 2022 and severe data fragmentation. Conventional reporting systems, dominated by manual mechanisms (85%), create a temporal crisis, causing response delays of 24 to 48 hours. This research aims to design and develop an integrated mobile application prototype that combines predictive Artificial Intelligence (AI) with community participation (crowdsourcing) to address this gap. The methodology used is Research and Development (R&D), beginning with an in-depth needs analysis of 150 respondents in Riau. A three-tier system architecture is implemented, consisting of a Mobile Layer (Flutter), a Firebase-based Backend as a Service (BaaS), and a Machine Learning Engine (TensorFlow) with a Random Forest (RF) model optimized for peatland characteristics. Initial results show an RF model accuracy of >= 80% on internal validation data and 90% user approval for the minimalist UI/UX design. This prototype is explicitly engineered to achieve a system response time of < 1 minute and a prediction accuracy of >= 85%, making it an innovative solution that enhances response speed, operational resilience, and disaster mitigation effectiveness in Forest and Land Fires-prone areas like Riau Province.
STRATEGI MITIGASI KEBAKARAN HUTAN DAN LAHAN BERBASIS AI DI RIAU Ali, Edwar; Djahara, Khairani; Pradewanta, Rian
Jusikom : Jurnal Sistem Komputer Musirawas Vol 10 No 2 (2025): Jurnal Sistem Komputer Musirawas DESEMBER
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jusikom.v10i2.2833

Abstract

Forest and land fires (Karhutla) are a significant environmental threat in Riau Province with substantial ecological, health, and economic impacts. This research develops an integrated artificial intelligence (AI)-based application for Karhutla mitigation. The method uses a quantitative approach with a system development design. The dataset includes 87,600 spatiotemporal data items (2020-2024) from MODIS/VIIRS, BMKG, and Sentinel-2. Machine learning models (Random Forest and XGBoost) were trained on the data for real-time hotspot prediction. The XGBoost model achieved an accuracy of 91.2% (AUC 0.871), outperforming RF (88.1%, AUC 0.847). The results are integrated into a Geographic Information System through three main modules: (1) Prediction and Visualization, (2) Early Warning, and (3) Reporting and Analysis. A usability test involving 15 field users resulted in a System Usability Scale score of 82.5 (Excellent). A 4-week implementation pilot achieved a detection rate of 88.9% and a suppression rate of 86.7%, reducing the response time from 4.2 hours to 1.1 hour. The application integrates solutions for real-world AI challenges: model drift (automated retraining), black box (SHAP interpretability), and knowledge gap (training program). The research demonstrates AI technology for disaster mitigation operations with an ROI of 480% and an (investment) payback period of 10.3 months.
Penerapan K-Means Clustering untuk Mengelompokkan Risiko Diabetes Berdasarkan Gaya Hidup dan Kesehatan Sigit, Rapel Aprilius; Rio, Unang; Efrizoni, Lusiana; Ali, Edwar
JATISI Vol 12 No 4 (2025): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v12i4.13292

Abstract

Diabetes mellitus is a chronic disease with a globally increasing prevalence, driven by modern lifestyle changes. Early detection of diabetes risk is crucial in preventing and mitigating long-term complications. This study aims to cluster individuals based on their diabetes risk levels using the K-Means Clustering algorithm by considering lifestyle and health condition attributes. The dataset used was obtained from the Kaggle platform, consisting of 5,452 entries and 22 attributes. The pre-processing stage involved data cleaning, normalization, and manual feature selection. The optimal number of clusters was determined using the Elbow Method, which indicated the best result at k = 3. Cluster quality evaluation was performed using the Davies-Bouldin Index (DBI), which yielded a score of 0.7678, indicating a reasonably good level of cluster compactness and separation. The final output formed three risk clusters: low, medium, and high, with distributions of 424, 819, and 615 records, respectively. This segmentation is expected to serve as a basis for healthcare institutions in designing more targeted and data-driven preventive interventions.
Co-Authors Adellia Meiriza Agnes Chrisnalia Agustin Agustin Andri Setiawan Asparizal Asri - Asri -, Asri Azmi , Muhammad Baehaqi Didik Sudyana Efrizoni, Lusiana Hadi Asnal, Hadi Hamdani - Hasibuan, Fadliansyah Helda Yenni, Helda Herwin Herwin Herwin, Herwin Junadhi Junadhi Junadhi, Junadhi Khairani Djahara Khairani Djahara, Khairani Koko Harianto Lestari, Fika Ayu Mardainis Meiriza, Adellia Nova Indriyani Novfuja, Elma Pradewanta, Rian Pratama, Farhan Rahmaddeni , Rahmaddeni Rahmaddeni Rahmaddeni Rahmiati Rahmiati Rahmiati Rahmiati Rian Pradewanta Rini Yanti, Rini Saputra Wijaya , Yansyah Setiawan, Hengki Sharon - Sharon -, Sharon Sigit, Rapel Aprilius Susandri, Susandri SUSANTI Susanti Susanti Susanti, Susanti Triyani Arita Fitri Unang Rio Wirta Agustin Yurnalis