Article Per Year (5 Year)
p-Index From 2021 - 2026
3.914
P-Index
This Author published in this journals
All Journal Jurnal Reka Lingkungan MATICS : Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology) Jurnal Edukasi dan Penelitian Informatika (JEPIN) REKAYASA Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer JOIV : International Journal on Informatics Visualization Sinkron : Jurnal dan Penelitian Teknik Informatika Journal of Natural Science and Integration MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer J-Dinamika: Jurnal Pengabdian Kepada Masyarakat Indonesian Physical Review JISKa (Jurnal Informatika Sunan Kalijaga) Journal of Information Systems and Informatics Scientific Journal of Informatics International Journal of Advances in Data and Information Systems Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Insearch: Information System Research Journal Journal Automation Computer Information System (JACIS) J-Intech (Journal of Information and Technology) Malcom: Indonesian Journal of Machine Learning and Computer Science Journal of Information Technology and Cyber Security Jurnal ilmiah teknologi informasi Asia Teknologi : Jurnal Ilmiah Sistem Informasi
Agung Teguh Wibowo Almais
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Aerospace Engineering Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Library & Information Science Physics Social Sciences Other

Published : 30 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 30 Documents
Search

 1   2   3 
Assessment of Post-Disaster Building Damage Levels Using Back-Propagation Neural Network Prediction Techniques Wibowo Almais, Agung Teguh; Fajrin, Rahma Annisa; Naba, Agus; Sarosa, Moechammad; Juhari, Juhari; Susilo, Adi
JOIV : International Journal on Informatics Visualization Vol 9, No 3 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.3.2711

Abstract

Indonesia is susceptible to natural disasters, with its geographical location being one of the contributing factors. To mitigate the harmful effects of natural catastrophes, a disaster emergency response must be undertaken, consisting of steps taken immediately following the event. These operations include rescuing and evacuating victims and property, addressing basic needs, providing protection, and restoring buildings and infrastructure. Accurate data is required for adequate recovery after a disaster. The Badan Penanggulangan Bencana Daerah (BPBD) oversaw disaster relief efforts, but faulty damage assessments slowed restoration. Surveyor subjectivity and differing criteria result in discrepancies between reported damage and reality, generating issues during the post-disaster reconstruction. The objective of this study is to develop a prediction system to measure the extent of damage caused by natural disasters to buildings. The five criteria that decide the level of building damage after a disaster are building conditions, building structure condition, physical condition of severely damaged buildings, building function, and other supporting conditions. The data used are from the BPBD of Malang city from 2019 to 2023. This system would allow surveyors to make speedy and objective evaluations. Five different models were tested using the Neural Network Backpropagation approach. Model A2 produces the highest accuracy of 93.81%. A2 uses a 40-38-36-34 hidden layer pattern, 1000 epochs, and a learning rate 0.1. These findings can lay the groundwork for advanced prediction models in post-disaster building damage evaluation research.
Multivariate LSTM for Drug Purchase Prediction in Pharmaceutical Management Brawijaya, Fanny; Almais, Agung Teguh Wibowo; Chamidy, Totok
Journal of Information System and Informatics Vol 7 No 4 (2025): December
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v7i4.1313

Abstract

This study aims to develop a structured approach to predict the number of hospital drug purchases using deep learning techniques. The Multivariate Long Short-Term Memory (LSTM) model is designed to capture temporal and contextual patterns including transaction time, polyclinic type, and drug type to improve the efficiency of pharmaceutical management. The model was tested using outpatient transaction data at RSIA Fatimah Probolinggo hospital in East Java, Indonesia, through three configurations (A, B, and C) to determine the optimal parameters. The best model, the Model B1, produces a Mean Absolute Error (MAE) value of 10.239, Mean Absolute Percentage Error (MAPE) of 1.976%, and the Coefficient of Determination (R²) of 0.199, which indicates a high degree of accuracy. The results of the study prove that multivariate LSTM is able to model complex intervariable dependencies and provide superior results than conventional forecasting methods. In practical terms, this model can be used as a decision-making tool for hospital management in planning drug procurement, optimizing inventory, and preventing shortages and overstocks. The application of this model contributes to data-driven pharmaceutical supply chain planning in smart hospital management systems.
XGBoost Model Optimization Using PCA for Classification of Cyber Attacks on The Internet of Things Ramadan, Afrijal Rizqi; Hariyadi, Mokhamad Amin; Almais, Agung Teguh Wibowo
International Journal of Advances in Data and Information Systems Vol. 6 No. 3 (2025): December 2025 - International Journal of Advances in Data and Information Syste
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v6i3.1465

Abstract

The rapid expansion of the Internet of Things (IoT) ecosystem has increased its susceptibility to cyberattacks, creating a critical need for reliable Intrusion Detection Systems (IDS). However, IDS performance is often hindered by severe class imbalance, high-dimensional features, and similarities among attack behaviors. This study proposes an optimized XGBoost model enhanced with the Synthetic Minority Over-sampling Technique (SMOTE) and Principal Component Analysis (PCA) to address these challenges. A systematic grid-search procedure was employed to ensure transparency, reproducibility, and optimal hyperparameter selection. The original imbalance ratio of approximately 1:27 was successfully normalized to nearly 1:1 through SMOTE. The Gotham dataset used in this study consists of roughly 350,000 IoT traffic records across eight attack categories. Five data-splitting scenarios (50:50 to 90:10) were evaluated using stratified hold-out validation supported by k-fold cross-validation. The optimized model achieved 99.68% accuracy, while extremely high AUC values approaching 1.0 were carefully validated to eliminate potential data leakage. Naive Bayes, Logistic Regression, Support Vector Machine, and Deep Neural Network were included as baseline comparisons. The results demonstrate that combining SMOTE and PCA significantly improves model stability and generalization on imbalanced IoT traffic, confirming the effectiveness of the proposed XGBSP method.
Prediction of State Civil Apparatus Performance Allowances Using the Neural Network Backpropagation Method Kurniawan, Puan Maharani; Almais, Agung Teguh Wibowo; Hariyadi, M. Amin; Yaqin, M. Ainul; Suhartono, Suhartono
JOIV : International Journal on Informatics Visualization Vol 7, No 3 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.3.1698

Abstract

Performance allowance is a form of appreciation given by an agency to its human resources. The Office of the Ministry of Religion of Batu City provides performance allowances to civil servants who work in the agency. Several things that affect the provision of performance allowances, such as grade, deduction, taxable income, income tax, and total tax, are used in this study to produce the total gross performance allowances and total performance allowances received. Based on the data obtained, there are some missing data from the parameters of taxable income, income tax, and total tax. This study aims to predict performance allowance when there is missing data. The method used is Neural Network Backpropagation. This study uses 480 data with split data ratios of 50:50, 60:40, 70:30, and 80:20, with epochs 40,000 and a learning rate 0,9. Four types of models used in this study are distinguished based on the number of hidden layers and epochs used. Model A uses two hidden layers to produce the highest accuracy with a 50:50 data split ratio of 65,16%. Model B uses four hidden layers to produce the highest accuracy with a 50:50 data split ratio of 69,34%. Model C uses six hidden layers to produce the highest accuracy with a 50:50 data split ratio of 68,18%. Model D uses eight hidden layers to produce the highest accuracy with a 50:50 data split ratio of 70,90%.
Analysis of the Use of Random Forest Models to Measuring the Quality of Indonesian Higher Education Institutions Wiyono, Masdar; Crysdian, Cahyo; Hariyadi, Mokhamad Amin; Abidin, Zainal; Almais, Agung Teguh Wibowo
Rekayasa Vol 18, No 3: Desember, 2025
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/rekayasa.v18i3.32024

Abstract

This study investigates the performance of the Random Forest algorithm in measuring the quality of Higher Education Institutions (HEIs) in Indonesia. The current reliance on administrative evaluations and conventional accreditation processes often fails to capture the institutions’ actual performance comprehensively, indicating the need for a data-driven alternative. This research proposes the use of a Random Forest–based classification model to assess institutional quality based on relevant accreditation indicators. The RF-D model demonstrates optimal classification performance across three quality categories—Good, Very Good, and Excellent—with high precision, recall, and F1-scores for all classes. The Very Good category achieves a precision of 89% and a recall of 80%, while the Excellent category records the highest recall at 86%. Furthermore, the Area Under Curve (AUC) scores, which approach 1.0 for all categories, confirm the strong discriminative capability of the model. This study also highlights the influence of train–test data ratios on model stability. Extreme imbalances in data splitting can lead to overfitting or underfitting, emphasizing the importance of selecting an appropriate configuration during model development. Overall, the findings indicate that Random Forest, when optimized with suitable parameters, provides a more accurate, objective, and replicable approach for evaluating HEI quality in Indonesia. These results are expected to contribute to the development of a more transparent higher education assessment system and support data-driven decision-making among policymakers.
Smart Assessment menggunakan Backpropagation Neural Network Agung Teguh Wibowo Almais; Cahyo Crysdian; Khadijah Fahmi Hayati Holle; Akbar Roihan
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 21 No. 3 (2022)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v21i3.1469

Abstract

Penerapan scraping dan Backpropagation Neural Network dapat menjadikan penilaian Self- Assessment Questionnaire (SAQ) website Pemerintah Daerah Provinsi Jawa Timur lebih smart jika dibandingkan dengan model assessment yang sudah ada. Langkah awal yaitu melakukan scraping website Pemerintah Daerah Provinsi Jawa Timur untuk mendapatkan nilai SAQ. Hasil scraping tersebut akan digunakan sebagai data uji pada metode Backpropagation Neural Network, kemudian hasil data uji akan di proses menggunakan 4 jenis model data yang berbeda-beda dari segi jumlah iterasi dan hidden layer untuk mendapatkan akurasi terbaik. Pada model data A menggunakan iterasi 1000 dan 5 hidden layer menghasilkan nilai Mean Squared Error (MSE) 0,0117, Mean Absolute Percent Error (MAPE) 39,36% dan Akurasi 60.64%. Model data B menggunakan iterasi 1000 dan 7 hidden layer menghasilkan nilai MSE 0,0087, MAPE 29,49% dan Akurasi 70,50%. Model data C dengan menggunakan iterasi 2000 dan 9 hidden layer menghasilkan nilai MSE 0,0064, MAPE 24,46% dan Akurasi 75,53%. Model data D menggunakan iterasi 2000 dan 9 hidden layer menghasilkan nilai MSE 0,0036, MAPE 18,71% dan Akurasi 81,28%. Dari hasil ujicoba tersebut bahwa model data D yang menggunakan iterasi 2000 dan 9 hidden layer menghasilkan tingkat akurasi yang terbaik sehingga model data D dapat dijadikan acuan hasil penilaian website Pemerintah Daerah Provinsi Jawa Timur tahun 2021.
Utilizing Long Short-Term Memory (LSTM) Networks for Predicting Seismic-Induced Building Damage: A Bawean Region Case Study Zarkoni, Ahmad; Almais, Agung Teguh Wibowo; Crysdian, Cahyo; Hariyadi, Mokhamad Amin; Pagalay, Usman; Sugiharto , Tomy Ivan
Jurnal Ilmiah Teknologi Informasi Asia Vol 20 No 1 (2026): Volume 20 Issue 1 2026 (8)
Publisher : LP2M Institut Teknologi dan Bisnis ASIA Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jitika.v20i1.1212

Abstract

This study examines the feasibility of employing Long Short-Term Memory (LSTM) networks to estimate earthquake-induced building damage using a focused dataset derived from the continuous 8-day mainshock–aftershock sequence that occurred in March 2024. A total of 483 events were analyzed, utilizing three readily available source parameters: magnitude, depth, and epicentral distance to predict the corresponding EMS-98 damage grade. The motivation for using an LSTM architecture stems from its capacity to model temporal dependencies within sequential seismic activity, despite the limited size of the dataset. The best-performing single-split model (B4) achieved a test R^2 of 0.5738 and an RMSE of 0.2997 on the held-out set. However, to obtain a more robust assessment of the model’s generalizability, a 5-fold TimeSeriesSplit cross-validation was conducted. The cross-validation procedure yielded a mean R^2 of 0.49 with a standard deviation of 0.27, and a mean RMSE of 0.33 with a standard deviation of 0.16. These results demonstrate that the LSTM model provides a credible baseline model for exploratory damage estimation, although a substantial portion of the variance remains unexplained due to the absence of geotechnical, soil amplification, and structural fragility information. The findings highlight the potential of sequence-based modeling for rapid damage estimation and underscore the need for integrating site-specific and structural variables in future work to enhance predictive accuracy.
A hybrid GoogLeNet–GLCM feature extraction framework for textural representation of post-disaster building damage imagery Amani, Holidiyatul; Almais, Agung Teguh Wibowo; Abidin, Zainal; Nugroho, Fresy; Kurniawan, Fachrul; Sugiharto , Tomy Ivan
Jurnal Ilmiah Teknologi Informasi Asia Vol 20 No 1 (2026): Volume 20 Issue 1 2026 (8)
Publisher : LP2M Institut Teknologi dan Bisnis ASIA Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jitika.v20i1.1214

Abstract

Accurate representation of visual characteristics in post-disaster building imagery is crucial for downstream analytical tasks such as damage interpretation, retrieval, and automated assessment. This study presents a focused investigation of feature extraction using a hybrid approach that integrates deep semantic representations from the GoogLeNet architecture with statistical texture descriptors inspired by the Gray-Level Co-Occurrence Matrix (GLCM). The objective of this work is limited strictly to the generation and analysis of semantic–textural feature vectors rather than the development or evaluation of any classification or prediction model. High-level feature maps are obtained from a selected convolutional layer of GoogLeNet, after which statistical texture properties—contrast, energy, and homogeneity—are computed per channel. A representative set of feature channels is analyzed to demonstrate the capabilities of the proposed hybrid extraction pipeline. The results demonstrate the potential of semantic–textural descriptors to provide interpretable feature characteristics in building-damage imagery. This study provides a methodological foundation and analytical insight for future works that may incorporate these feature representations into classification, clustering, or decision-support frameworks.
KARAKTERISASI POLIMER MIKROPLASTIK DI PERAIRAN LOMBOK MENGGUNAKAN SPEKTROSKOPI FTIR-ATR (ATTENUATED TOTAL REFLECTANCE) Anton Prasetyo; Tri Kustono Adi; Agung Teguh Wibowo Almais; Rif'atul Mahmudah; Tri Harningsih; Alfina Taurida Alaydrus
Jurnal Reka Lingkungan Vol 13, No 2 (2025)
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/rekalingkungan.v13i2.193-203

Abstract

Mikroplastik merupakan partikel plastik berukuran <5 mm yang telah menjadi polutan global di berbagai ekosistem akuatik termasuk perairan Lombok. Penelitian ini bertujuan untuk mengidentifikasi jenis polimer mikroplastik yang terdapat di perairan Lombok menggunakan teknologi Fourier Transform Infrared-ATR. Sepuluh sampel mikroplastik (MCP1-MCP10) dikumpulkan dari berbagai lokasi di perairan Lombok pada tahun 2025. Analisis FTIR dilakukan dengan resolusi 4 cm⁻¹ terhadap semua sampel untuk mengidentifikasi gugus fungsi karakteristik dari setiap polimer. Hasil penelitian menunjukkan bahwa perairan Lombok terkontaminasi oleh lima jenis polimer utama: Polyethylene (PE) 40%, Polyvinyl Chloride (PVC) 20%, Polypropylene (PP) 10%, Polystyrene (PS) 10%, dan Polyethylene Terephthalate/Polyamide (PET/PA) 20%. PE dan PVC merupakan polimer paling dominan, diindikasikan oleh puncak spektral khas pada bilangan gelombang 540-700 cm⁻¹ dan 2900 cm⁻¹. Potensi sumber kontaminan diduga berasal dari aktivitas pariwisata, perikanan, pemukiman pesisir, dan limbah domestik. Penelitian ini memberikan wawasan penting tentang komposisi polimer mikroplastik di perairan Lombok dan dasar untuk kebijakan pengelolaan limbah plastik yang lebih efektif di wilayah pesisir.
Optimalisasi Chatbot Berbasis TinyLLaMA dengan Fine - Tuning LoRA pada Sistem Layanan Agensi Property Fachrizal Fazza Ashari; Agung Teguh Wibowo Almais; Fajar Rohman Hariri
TEKNOLOGI: Jurnal Ilmiah Sistem Informasi Vol 16 No 1 (2026): January
Publisher : Universitas Pesantren Tinggi Darul 'Ulum (Unipdu) Jombang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/teknologi.v16i1.6433

Abstract

Industri properti di Indonesia menghadapi tantangan dalam menyediakan layanan konsultasi yang cepat, responsif, dan efisien kepada calon pembeli. Model pemasaran tradisional dinilai kurang mampu memenuhi kebutuhan interaksi real-time yang semakin tinggi di era digital. Penelitian ini bertujuan mengembangkan chatbot konsultan properti berbahasa Indonesia menggunakan model TinyLLaMA-1.1B-Chat yang diadaptasi melalui metode fine-tuning Low-Rank Adaptation (LoRA) pada lapisan query projection (q_proj) dan value projection (v_proj). Dataset sintetis dikonstruksi menggunakan pendekatan Template-Based Data Generation yang mencakup tujuh kategori intent, yaitu simulasi KPR, dokumen legal, biaya dan pajak, spesifikasi properti, proses transaksi, konsultasi keputusan, serta risiko dan disclaimer. Eksperimen dilakukan pada tiga konfigurasi model dengan variasi nilai rank LoRA untuk menganalisis pengaruhnya terhadap kualitas dialog. Evaluasi dilakukan menggunakan metrik BLEU-4 serta kuesioner pengguna. Hasil eksperimen menunjukkan bahwa Skenario 3 dengan konfigurasi rank r=24 dan lora_alpha=48 menghasilkan performa terbaik secara kuantitatif dengan skor BLEU-4 sebesar 16.57, mengungguli Skenario 1 (15.27) dan Skenario 2 (13.39). Hasil evaluasi pengguna mengindikasikan bahwa chatbot mampu menangani pertanyaan rutin secara efektif dengan performa yang sebanding dengan agen manusia, sehingga pendekatan hybrid antara chatbot dan agen manusia direkomendasikan untuk mengoptimalkan layanan secara menyeluruh.
Co-Authors A Basid, Puspa Miladin Nuraida Safitri A'la Syauqi AA Sudharmawan, AA Abd. Rouf Abdurrosyid, R. Adi Susilo Adinda Dhea Pramitha Agus Naba Ainafatul Nur Muslikah Ainul Yaqin Akbar Roihan Akkad, Muhammad Iqbal Alfina Taurida Alaydrus Alif Pahlevi, Achmad Fahreza Alviola, Nuril Afni Amani, Holidiyatul Anis Fatul Fu'adah Anisa Anisa Aniss Fatul Fu'adah Anton Prasetyo Aprilia, Faridha Arief, Yunifa Miftachul Artimordika, Firgy Aulia A’la Syauqi Brawijaya, Fanny Bunga Puspita, Mayang Cahyo Crysdian Dyah Ayu Wiranti Dyah Febriantina Istiqomah Dyah Wardani Fachrizal Fazza Ashari Fachrul Kurniawan Fajar Rohman Hariri Fajrin, Rahma Annisa Farhanah, Nisrina Darin Fresy Nugroho Habibiy Idmi, Mohammad Halimahtus Mukminna, Halimahtus Hariyadi, Mokhammad Amin Jesi Alexander Alim Juhari Juhari, Juhari Khadijah Fahmi Hayati Holle Kurnia Siwi Kinasih Kurniawan, Puan Maharani Kusuma, Selvia Ferdiana Laela Nurul Qomariyah Mandiro, Mulia Anton Mochamad Imamudin Moechammad Sarosa Mokhamad Amin Hariyadi Muhammad Aji Pangestu Muhammad Aziz Muslim Muhammad Fathur Rouf Hasan Muwardi Sutasoma Neni Hermita Ningtias, Nadila Oktavia Pizaini Pizaini Putri Purnamasari Rahmatmulya, Revaldi Ramadan, Afrijal Rizqi Rif&#039;atul Mahmudah Ririen Kusumawati Rizal Furqan Ramadhan Roro Inda Melani Safitri, Annisa Heparyanti Sa’adah Rahmaningtyas, Nilmadiana Nur Shinta Rizki Firdina Sugiono Sri Herwiningsih Sugiharto , Tomy Ivan Syahiduz Zaman Syauqi, A'la Syauqi, A’la Syawab, Moh Husnus Tanti Rismawati Thahir, Musa Totok Chamidy Tri Harningsih Tri Kustono Adi Usman Pagalay Vebrianto, Rian Wardana, M. Dafa Wiyono, Masdar Zainal Abidin Zarkoni, Ahmad