Article Per Year (5 Year)
p-Index From 2021 - 2026
2.149
P-Index
This Author published in this journals
All Journal Jurnal Edukasi Elektro PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Jurnal Riset Informatika Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Ilmu Komputer dan Sistem Komputer Terapan (JIKSTRA) Jurnal Sains Teknologi dan Sistem Informasi KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika Jurnal Pepadun Informatics and Computer Engineering Journal Jurnal Teknik Informatika Jurnal Masyarakat Madani Indonesia EdLib Journal (Education and Library Journal)
Akhiyar Waladi
Universitas Jambi
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Library & Information Science Public Health Social Sciences Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Analisis Prediktif Tren Pendidikan di Indonesia Menggunakan KNN Studi Kasus Data Pendidikan 2021-2023 Nasution, Mukhtada Billah; Akhiyar Waladi; Ulfa Khaira; Pradita Eko Prasetyo Utomo
Education Library Vol. 2 No. 1 (2025): Education and Library Journal
Publisher : UPT Perpustakaan Universitas Jambi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research focuses on the importance of education in improving the competitiveness of the younger generation in Indonesia, especially in facing the challenges of globalization and the digital revolution. Education trends in Indonesia during the 2021-2023 period have been dominated by two main factors, namely digitalization and equal access to education. A data-driven approach is used to predict education trends in 2024, using the K-Nearest Neighbor (KNN) algorithm to analyze data from the Central Statistics Agency (BPS) regarding the percentage of the population aged 25 years and over who have at least a high school education, categorized by gender. The result of this research will predict the trend of education in each region in 2024 whether it is decreasing, stable, or increasing. Through data collection and literature study, this research identifies relevant patterns and presents statistically-based predictions that can serve as a reference for stakeholders in the development of education in Indonesia. The results of this study are also expected to provide insights for policymakers in formulating effective strategies to address the education gap and promote inclusive digitalization..
Peningkatan Akurasi Klasifikasi Tutupan Lahan Menggunakan Random Forest pada Data Sentinel-2 di Jambi Waladi, Akhiyar
JURNAL FASILKOM Vol. 15 No. 1 (2025): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v15i1.8886

Abstract

Klasifikasi tutupan lahan yang akurat memainkan peran penting dalam pemantauan lingkungan, perencanaan perkotaan, dan pengelolaan sumber daya berkelanjutan. Dengan meningkatnya kekhawatiran terhadap perubahan penggunaan lahan dan degradasi ekologis, pengembangan metode klasifikasi yang efektif menjadi semakin penting, terutama di wilayah yang mengalami transformasi lanskap secara cepat. Penelitian ini mengevaluasi kinerja tujuh algoritma machine learning (Random Forest, Extra Trees, Logistic Regression, Decision Tree, Naive Bayes, SGD Classifier, dan LightGBM) untuk klasifikasi tutupan lahan menggunakan data satelit Sentinel-2 di wilayah Jambi. Studi ini menggunakan 23 fitur, termasuk 10 band spektral dan 13 indeks spektral, dengan data yang dikumpulkan selama Q4 2024. Hasil menunjukkan bahwa Random Forest mencapai kinerja terbaik secara keseluruhan dengan akurasi 85.91% dan weighted F1-score 85.48%, diikuti oleh Extra Trees dengan akurasi 84.45%. Algoritma berbasis pohon keputusan menunjukkan kemampuan yang lebih unggul dalam membedakan area perkotaan, vegetasi, dan badan air, meskipun semua algoritma menghadapi tantangan dengan kelas minoritas. Temuan ini merepresentasikan peningkatan signifikan dibandingkan pendekatan sebelumnya yang hanya mencapai akurasi 37.7%-66.9% menggunakan indeks vegetasi tunggal. Peningkatan akurasi klasifikasi memungkinkan pemantauan yang lebih efektif terhadap deforestasi, ekspansi perkotaan, dan perubahan ekosistem di wilayah tropis, memberikan dukungan penting bagi kebijakan pengelolaan lahan berbasis bukti dan strategi konservasi di lanskap kompleks seperti Jambi.
Pengelompokan Provinsi Di Indonesia Berdasarkan Rasio Penggunaan Gas Rumah Tangga Pada Tahun 2023 Menggunakan Hierarchical Clustering Nasution, Afdal Aditya; Eko Prasetyo Utomo, Pradita; Ulfa Khaira; Akhiyar Waladi
JEKIN - Jurnal Teknik Informatika Vol. 5 No. 1 (2025)
Publisher : Yayasan Rahmatan Fidunya Wal Akhirah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58794/jekin.v5i1.1232

Abstract

Penggunaan energi gas rumah tangga merupakan aspek penting yang mencerminkan aksesibilitas dan distribusi energi di berbagai wilayah Indonesia. Penelitian ini bertujuan untuk mengelompokkan provinsi-provinsi di Indonesia berdasarkan pola penggunaan gas rumah tangga menggunakan metode klasterisasi hierarki dengan pendekatan average linkage. Data yang digunakan bersumber dari Badan Pusat Statistik (BPS) dan telah melalui proses praproses untuk memastikan kebersihan dan konsistensi data. Evaluasi hasil klasterisasi dilakukan dengan membandingkan nilai rata-rata Silhouette Coefficient pada jumlah klaster yang berbeda, menunjukkan bahwa dua klaster merupakan jumlah optimal, dengan pemisahan antar kelompok yang signifikan dan kohesi yang tinggi dalam setiap klaster. Hasil klasterisasi ini memberikan gambaran yang jelas mengenai pola penggunaan gas di Indonesia, dengan rata-rata rasio penggunaan gas rumah tangga tahun 2023 pada klater 1 adalah 90,02 atau 90,02%. Dan rata-rata rasio penggunaan gas rumah tangga tahun 2023 pada klater 2 adalah 2,3 atau 2,3%.
Parameter-Efficient Models for Malaria Detection and Classification Using Small-Scale Imbalanced Blood Smear Images Akhiyar Waladi; Hasanatul Iftitah; Nindy Raisa Hanum; Yogi Perdana; Fitra Wahyuni; Rahmad Ashar
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 11, No. 2, May 2026
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v11i2.2558

Abstract

Malaria diagnostic automation faces critical challenges, including severe class imbalance with ratios of up to 54:1, limited datasets containing 200 to 500 images, and computational inefficiency resulting from the need to train separate models for each detection-classification combination. This study developed a multi-model framework with a shared classification architecture that trains classification models once on ground-truth crops and reuses them across all detectors. The framework systematically evaluated three YOLO Medium architectures for parasite detection and six CNN architectures for lifecycle and species classification across four complementary malaria datasets totaling 1,544 microscopy images. Detection achieved mAP@50 scores ranging from 70.84% to 96.27%, with high recall values of 71.05% to 93.12% minimizing missed parasite detections. Classification results demonstrated the importance of dataset-dependent model selection, with parameter-efficient EfficientNet models containing 5.3M to 9.2M parameters consistently outperforming ResNet variants with up to 44.5M parameters. EfficientNet-B1 achieved accuracies of 91.51% on the IML Lifecycle dataset and 98.28% on the MP-IDB Species dataset, while EfficientNet-B0 achieved 86.45% on the multi-patient MD-2019 dataset. ResNet50 achieved 96.13% accuracy on severely imbalanced MP-IDB Stages dataset. Focal Loss optimization with alpha = 1.0 and gamma = 1.5 enabled robust minority-class performance, achieving F1-scores between 0.44 and 1.00 on ultra-minority classes and demonstrating effective handling of class imbalance. The compact models, with sizes ranging from 46 MB to 89 MB, enable practical deployment on resource-constrained hardware.
Evaluating Kolmogorov-Arnold Networks for Multispectral Land Cover Classification Using Sentinel-2 Imagery in Jambi City Akhiyar Waladi; Hasanatul Iftitah
Jurnal Pepadun Vol. 7 No. 1 (2026): April
Publisher : Department of Computer Science, Faculty of Mathematics and Natural Sciences, University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/pepadun.v7i3.334

Abstract

Land cover maps obtained from satellite imagery are used in environmental management and spatial planning. Deep learning now outperforms traditional machine learning for this task, but Kolmogorov-Arnold Networks (KAN) have rarely been tested on multispectral remote sensing data. This paper evaluates two KAN strategies for classifying nine land cover types from Sentinel-2 imagery in Jambi, Indonesia. ResNet-KAN adds a KAN-based classifier head to a standard CNN backbone, while ConvKAN builds the entire network from KAN-based convolution layers. Both are compared against seven CNN, Transformer, and machine learning baselines using 23 spectral features with Google Dynamic World labels as reference, and ablation experiments test spectral feature composition, ImageNet transfer learning, and input patch size. Swin Transformer reaches the highest overall accuracy (88.34%), but ConvKAN better separates rare land cover classes like Grass and Shrub, achieving the best F1-Macro (0.5870) with only 2.91 million parameters, 89.4% fewer than Swin-T. Adding spectral indices raises ConvKAN F1-Macro by 13.8%, but lowers ViT accuracy by 3.19% OA because self-attention can already learn band-ratio operations from raw bands. KAN models also perform better when trained from scratch, because most Sentinel-2 channels fall outside the visible spectrum that ImageNet covers. Spatially, ConvKAN produces maps as clean as Swin Transformer despite being ten times smaller. KAN can therefore match larger models in accuracy and map quality for multispectral land cover classification.
Comparative Analysis of Triangulation Methods for Optimal Solutions to the Art Gallery Problem Jefri Marzal; Niken Rarasati; Akhiyar Waladi; Yogi Perdana
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 13 No. 1 (2025): Maret 2025
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v13i1.10749

Abstract

Triangulation is the process of breaking down an n-sided polygon into triangles and it is necessary in deciding the optimal count and the position of guards in the Art Gallery Problem (AGP) There is a theoretical limit that has been established which states that the number of required guards needed to keep an eye on such a polygon is ⌊n/3⌋ and this research considers this as the limit. Among various triangulation methods, Ear Clipping and Minimum Weight are two primary approaches frequently used to achieve optimal solutions. Nonetheless, its comparison with other methods, more particularly the amount of guards required for the maximum theoretical figure, is still a gap in literature. The aim of this research is to create an AGP simulation program and test it against the theoretical upper bound, determining the number of guards required. 228 simple polygons with vertices varying between 10 and 110 were utilized in this research. The polygons were classified into three groups based on the ratio of convex to concave vertices: less concave vertices, equal amount of concave and convex vertices and vice versa. Result study shows that the Ear Clipping method is significantly superior to Minimum Weight in reducing guard requirements. Practically speaking, these advancements are important for the design of engineering systems such as surveillance systems and the surveillance of public spaces. In the context of building security system design and monitoring of large areas, these conclusions are of utmost importance.
Multimodal Learning Menggunakan Efficientnetv2 Dan Distilbert Untuk Deteksi Website Ilegal Dan Implementasinya Pada Browser Extension Sahal Maghfud; Ulfa Khaira; Akhiyar Waladi
Jurnal Ilmu Komputer dan Sistem Komputer Terapan (JIKSTRA) Vol. 8 No. 1 (2026): Edisi April
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

To address the ineffectiveness of domain blocking for illegal content such as online gambling, pornography, and piracy in Indonesia due to VPNs or new domains, this study proposes a Chromium extension based on multimodal learning. It fuses visual features using EfficientNetV2 M, text using multilingual DistilBERT, and HTML structure via early fusion into a vector of 2,187 dimensions, which is then classified by an MLP into four categories namely normal, online gambling, pornography, and piracy. Using a completely novel dataset consisting of 16,224 samples, the text and image combination achieved the best performance with an accuracy of 88.74%, a Macro F1 Score of 0.8275, and a Macro Recall of 0.812. For real world robustness, the extension utilizes all three modalities comprising text, image, and HTML, successfully classifying 36 of 40 unseen websites. Misclassifications occurred only in the digital piracy category due to limited training data and high visual similarity to legitimate websites..  
TRANSFER LEARNING ARCHITECTURE SELECTION FOR REMOTE SENSING SCENE CLASSIFICATION Akhiyar Waladi; Hasanatul Iftitah
Jurnal Riset Informatika Vol. 8 No. 3 (2026): Juni 2026
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v8i3.515

Abstract

Selecting a deep learning architecture for classifying remote sensing scenes usually involves comparing published accuracy across papers that each use different training protocols, making it unclear whether accuracy gaps reflect architecture or training differences. We isolate the architecture variable by evaluating eight models from three design families, five classical CNNs (ResNet-50, ResNet-101, DenseNet-121, EfficientNet-B0, EfficientNet-B3), two vision transformers (ViT-B/16, Swin Transformer), and one modernized CNN (ConvNeXt-Tiny), under identical training conditions on EuroSAT (10 classes, 27,000 Sentinel-2 patches) and UC Merced (21 classes, 2,100 aerial photographs). Every model shares the same ImageNet-1K initialization, AdamW optimizer, augmentation pipeline, and early stopping rule. ConvNeXt-Tiny reached the highest accuracy on EuroSAT (99.11%) and Swin-T on UC Merced (99.76%), but the accuracy range on EuroSAT was only 0.41 percentage points (1.66 on UC Merced). McNemar's test confirmed that most pairwise differences were not significant. EfficientNet-B0, the smallest model at 4.0M parameters, reached 98.76% and 99.52% while using 21x fewer parameters than ViT-B/16. On these two well-studied benchmarks, a single uniform training configuration was sufficient to bring all architectures to near-identical performance. This convergence, observed under one fixed protocol and a single data partition, suggests that on saturated classification tasks the choice of architecture may be secondary to the choice of training procedure. Whether this convergence holds on harder benchmarks, under architecture-specific optimal configurations, or with domain-specific pretraining remains to be tested
Design and Development of a Multi-Blade Horizontal Axis Wind Turbine as an Alternative Energy Source in Talang Solok Regency Fiqri Al Faruqi; Yendri Modika; Andre Rabiula; Dasrinal Tessal; Akhiyar Waladi; Lailal Gusri; Ali Satria Wijaya; Andicho Haryus Wirasapta; Dewi Triantini
Jurnal Edukasi Elektro Vol. 10 No. 1 (2026): Jurnal Edukasi Elektro Volume 10, No. 1, May 2026
Publisher : DPTE FT UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jee.v10i1.91466

Abstract

Indonesian rural and highland areas have considerable potential for developing small-scale renewable energy, especially utilizing wind resources with low to moderate wind speeds. This research outlines the creation, design, and assessment of a six-blade horizontal axis wind turbine (HAWT) aimed at facilitating off-grid and decentralized electricity production in Talang, Solok Regency. To enhance the design methodology, a comparative design evaluation was performed by analyzing three-blade, four-blade, and six-blade rotor setups concerning starting torque traits, suitability for low wind speeds, and operational stability documented in earlier research. The six-blade design was chosen for its improved self-starting ability and dependable performance at wind speeds under 7 m/s. The created prototype features a rotor diameter of 1.5 m, a blade length of 0.75 m, a 1:5 gear ratio, and a 200 W DC generator. Performance testing took place over two months (August–September 2025) in natural wind conditions varying between 4.8 and 7.1 m/s. The turbine produced an open-circuit voltage of 2.5–4.4 V, and when under load, the peak electrical power output was 1.52 W. The determined power coefficient (Cp) varied from 0.12 to 0.18, demonstrating efficient energy conversion in low-speed wind conditions. The findings indicate that the suggested multi-blade HAWT design provides a technically viable, context-suitable, and scalable option for rural electrification, community-level renewable energy systems, and educational uses in areas with comparable wind conditions.
Pemodelan Prediksi Magnitudo Gempa Bumi di Indonesia Periode 2023–2025 Menggunakan Algoritma Naive Bayes M. Faris Daffarindra; Akhiyar Waladi; Pradita Eko Prasetyo Utomo; Ulfa Khaira
KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika Vol 7, No 1 (2026)
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.kernel.2026.v7i1.8399

Abstract

Prediksi gempa bumi sangat penting untuk mitigasi bencana di Indonesia sebagai salah satu negara paling aktif seismik di dunia. Penelitian ini menerapkan algoritma Gaussian Naïve Bayes untuk mengklasifikasikan magnitudo gempa menggunakan data BMKG periode 2023-2025. Setelah pra-pemrosesan 30.000 rekaman, diperoleh 23.979 data valid dengan enam variabel prediktor: lintang, bujur, kedalaman, phasecount, azimuth gap, dan jenis magnitudo. Magnitudo dikelompokkan menjadi Ringan ( 3,0), Sedang (3,0-4,9), dan Kuat (≥ 5,0). Model mencapai akurasi 71,68% dengan precision 0,77 dan recall 0,66 pada kelas Sedang, serta recall 0,78 pada kelas Ringan. Validasi 5-fold cross-validation menghasilkan rata-rata akurasi 68,78% (±7,32%). Perbandingan dengan Random Forest (83,63%) dan SVM (79,15%) menunjukkan hanya Naïve Bayes yang mampu mendeteksi kelas Kuat (precision = 0,18; recall = 0,25). Kebaruan penelitian ini terletak pada evaluasi komparatif tiga algoritma dan analisis kritis asumsi independensi fitur Naïve Bayes terhadap data seismik nyata. Model ini layak sebagai alat skrining awal dalam sistem peringatan dini.
Co-Authors Ali Satria Wijaya Andicho Haryus Wirasapta Andre Rabiula Dasrinal Tessal Dewi Triantini Edi Saputra Eko Prasetyo Utomo, Pradita Fauzi Nurhamdi Fiqri Al Faruqi Fitra Wahyuni Hasanatul Iftitah Hasanatul Iftitah Hasby Kuswanto Jefri Marzal Khaira, Ulfa Lailal Gusri M. Faris Daffarindra M. Rizky Ardiansyah Putra Nasution, Afdal Aditya Nasution, Mukhtada Billah Niken Rarasati Nindy Raisa Hanum Nindy Raisa Hanum Nindy Raisa Hanum Pradita Eko Prasetyo Utomo Rahmad Ashar Rahmad Ashar Sahal Maghfud Syamsyida Rozi Ulfa Khaira Ulfa Khaira Utomo, Pradita Eko Prasetyo Yendri Modika Yogi Perdana Yogi Perdana