Article Per Year (5 Year)
p-Index From 2021 - 2026
1.518
P-Index
This Author published in this journals
All Journal Jurnal Inotera JISKa (Jurnal Informatika Sunan Kalijaga) INFORMATIKA Computing and Education Technology Journal Buletin Ilmiah Ilmu Komputer dan Multimedia (BIIKMA) Jurnal Ilmu Komputer dan Sistem Informasi Journal of Innovative and Creativity JUPIKMAS Teknik: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Agus Heri Yunial
Universitas Pamulang
Humanities Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Social Sciences Other

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Analisis Sentimen pada Ulasan Aplikasi FinTech di Indonesia: Studi Komparatif Model Machine Learning dan Deep Learning Ahmad Fauzi; Achmad Lutfi Fuadi; Agus Heri Yunial; Andrian Hidayat; Ade Napila
Journal of Innovative and Creativity Vol. 6 No. 1 (2026)
Publisher : Fakultas Ilmu Pendidikan Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/joecy.v6i1.6939

Abstract

Pertumbuhan sektor Teknologi Finansial (FinTech) telah menjadikan umpan balik pelanggan dari platform digital sebagai sumber penting untuk pengambilan keputusan strategis. Namun, volume dan ketidakstrukturan data, khususnya dalam bahasa informal seperti Bahasa Indonesia, menimbulkan tantangan analitis yang signifikan. Penelitian ini bertujuan untuk mengidentifikasi pipeline optimal untuk klasifikasi sentimen pada ulasan pengguna Livin' by Mandiri, super-app perbankan digital Indonesia. Kami melakukan analisis komparatif menggunakan dataset dunia nyata berisi 117.471 ulasan yang tidak seimbang (55% negatif, 31% positif, 14% netral) yang dibersihkan dari Google Play Store. Dua teknik vektorisasi teks, Bag-of-Words (BoW) dan TF-IDF, diuji pada empat classifier machine learning: Random Forest, Logistic Regression, Decision Tree, dan SVM, serta dibandingkan dengan model Deep Learning berbasis Long Short-Term Memory (LSTM). Hasilnya menunjukkan bahwa model LSTM unggul dengan akurasi 98,02% dan weighted F1-score 0,99, sementara model machine learning terbaik, Logistic Regression dengan TF-IDF, menghasilkan weighted F1-score 0,92. Temuan ini menegaskan bahwa meskipun machine learning tradisional efektif, LSTM lebih unggul dalam menangkap konteks dalam data sekuensial yang kompleks dan tidak seimbang. Penelitian ini menawarkan kerangka kerja yang berguna bagi institusi keuangan untuk menerapkan sistem analisis sentimen otomatis yang akurat dan efektif.
Optimalisasi Random Forest untuk Sentimen Bahasa Indonesia dengan GridSearch dan SMOTE Ahmad Fauzi; Agus Heri Yunial; Dede Eko Saputro; Reza Saputra
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 4 No. 2 (2025): Mei 2025
Publisher : LKP Unity Academy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70340/jirsi.v4i2.207

Abstract

This research focuses on optimizing the Random Forest algorithm for sentiment analysis of social media x in Indonesian using TextBlob as a labeling tool, followed by the SMOTE data balancing technique and hyperparameter optimization with GridSearch. The data used was taken from 611 tweets with the keyword ukt (single tuition). Sentiment labeling using TextBlob produces 438 negative sentiments and 173 positive sentiments. The SMOTE method is used to balance the data by first dividing the data into 75% training data and 25% test data. Data vectorization using tf-idf. The Random Forest algorithm model was evaluated with an initial accuracy using split data of 73%, and cross validation evaluation with 10 k-folds produced an accuracy value of 75%. Optimization carried out with GridSearch hyperparameters succeeded in increasing the accuracy value to 74%, while cross validation evaluation using 10 k-fold accuracy was 89%. In this research, the SMOTE method was effective in balancing unbalanced data, and gridsearch hyperparameter optimization succeeded in increasing the accuracy value of the Random Forest algorithm in classifying social media sentiment x in Indonesian with automatic texblob labeling.
Pembuatan Aplikasi Berbasis Web untuk Pengelolaan Tugas dan Jadwal di Madrasah Diniyah Takmiliyah (MDT) Menggunakan Metode Design Thinking Azriel Akbar Dinar; Agus Heri Yunial
Buletin Ilmiah Ilmu Komputer dan Multimedia Vol 4 No 1 (2026): Buletin Ilmiah Ilmu Komputer dan Multimedia (BIIKMA)
Publisher : Shofanah Media Berkah

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

Abstract

Pengelolaan jadwal pembelajaran dan tugas di Madrasah Diniyah Takmiliyah (MDT) yang masih dilakukan secara manual menimbulkan berbagai kendala, seperti keterlambatan penyampaian informasi, benturan jadwal, dan kesulitan dalam pengelolaan tugas. Penelitian ini bertujuan merancang dan membangun aplikasi berbasis web untuk membantu pengelolaan jadwal dan tugas secara lebih efektif dan terorganisir. Metode yang digunakan adalah Design Thinking yang meliputi tahapan Empathize, Define, Ideate, Prototype, dan Test. Data penelitian diperoleh melalui observasi, wawancara, dan studi pustaka. Sistem dikembangkan menggunakan PHP, HTML, CSS, JavaScript, MySQL, dan XAMPP. Hasil penelitian menunjukkan bahwa aplikasi mampu mempermudah pengelolaan jadwal, pemberian tugas, serta penyampaian informasi kepada admin, pengajar, dan santri. Pengujian fungsional dengan metode Black Box menunjukkan seluruh fitur berjalan sesuai kebutuhan, sementara hasil evaluasi melalui kuesioner memperoleh tingkat kepuasan pengguna sebesar 94,30%, yang termasuk kategori sangat baik. Dengan demikian, aplikasi yang dikembangkan dapat mendukung digitalisasi pengelolaan jadwal dan tugas di Madrasah Diniyah Takmiliyah secara efektif.
Comparative Analysis of Hybrid CNN-ViT and CNN for Brain Tumor Classification Ahmad Fauzi; Achmad Lutfi Fuadi; Agus Heri Yunial
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 11 No. 1 (2026): January 2026
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.5860

Abstract

The automated categorization of brain cancers from MRI is essential for improving diagnostic precision. Traditional Convolutional Neural Networks (CNNs) are proficient in local feature extraction but are constrained in their ability to capture long-range spatial relationships, hence impairing performance on intricate malignancies. We propose a hybrid parallel architecture that merges a CNN with a Vision Transformer (ViT) to combine local and global feature modeling. We assessed our dual-branch model in comparison to a conventional CNN baseline using a curated dataset of 15,000 MRI images categorized into three classes: glioma, meningioma, and pituitary. The hybrid model exhibited enhanced performance, attaining 98.40% accuracy and 0.0783 loss, in contrast to the baseline's 97.40% accuracy and 0.1187 loss. The substantial decrease in misclassifications was validated by additional metrics, such as enhanced recall for the meningioma category. The integration of local and global variables produces a more precise, stable, and generalizable classification framework, demonstrating significant potential as a basis for dependable AI-driven Clinical Decision Support Systems (CDSS) in neuroradiology.
Edukasi Literasi Digital Untuk Mendorong Penggunaan Internet Yang Sehat Pada Pelajar SMK Panti Karya 3 Willis Puspita Sari; Agus Heri Yunial; Joko Suwarno
Jurnal Pengabdian kepada Masyarakat Indonesia Vol 1 No 3 (2026): April-Juni
Publisher : Samudra Ilmu Indonesia

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

Abstract

Perkembangan teknologi informasi dan internet memberikan berbagai kemudahan bagi masyarakat, khususnya pelajar. Internet dapat mendukung kegiatan pembelajaran, komunikasi, dan pencarian informasi. Namun, penggunaan yang tidak tepat juga dapat menimbulkan dampak negatif, seperti kecanduan gim, penggunaan media sosial secara berlebihan, akses terhadap informasi yang tidak sesuai, serta penyebaran informasi palsu. Pelajar SMK berada pada tahap perkembangan yang memiliki rasa ingin tahu tinggi dan mudah dipengaruhi lingkungan sekitarnya, sehingga diperlukan pemahaman dalam menggunakan internet secara bijak. Kegiatan ini bertujuan memberikan edukasi literasi digital kepada siswa SMK Panti Karya 3 agar mampu memanfaatkan internet secara sehat, aman, dan bertanggung jawab. Edukasi diberikan melalui penyampaian materi dan sesi tanya jawab mengenai penggunaan internet, keamanan informasi pribadi, penyaringan informasi, serta berbagai risiko dan dampak negatif penggunaan internet.
Analisis Dan Perancangan Infrastruktur Informasi Registrasi Online dengan Penggabungan Sistem Pembayaran Online Mengunakan Structured System Analysis And Design (SSADM) SD Islam Tahfiz Quran Daarussunnah Dennis Eka Putra; Agus Heri Yunial
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 6 No. 1 (2026): Maret : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v6i1.10456

Abstract

Abstract. Digital transformation in education requires efficient administrative systems to overcome manual process limitations. This research analyzes and designs an online registration information infrastructure integrated with digital payment systems at SD Islam Tahfiz Quran Daarussunnah using Structured System Analysis and Design Method (SSADM) methodology. System design utilizes Entity Relationship Diagrams, Logical Record Structures, and Unified Modeling Language to construct robust database architecture. Implementation employs Laravel framework with Midtrans payment gateway integration enabling various digital payment methods accompanied by automatic WhatsApp notifications and PDF transaction receipt printing. Black Box testing validates system functionality, White Box Testing yields cyclomatic complexity value of 2, while User Response evaluation involving 34 respondents demonstrates high satisfaction levels with 68.24% extremely satisfied with design and performance, and 71.76% with overall satisfaction. This system significantly enhances administrative process efficiency, data recording accuracy, and payment transaction transparency, simultaneously eliminating risks of physical document loss and manual data entry errors frequently occurring in conventional systems.
Benchmarking Deep Learning Models for Multi-Class Fruit Quality and Formalin Contamination Detection in Horticultural Fruits Ahmad Fauzi; Achmad Lutfi Fuadi; Agus Heri Yunial
Jurnal Inotera Vol. 11 No. 2 (2026): July - December 2026
Publisher : LPPM Politeknik Aceh Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31572/inotera.Vol11.Iss2.2026.ID732

Abstract

The adulteration of fresh horticultural produce with formaldehyde (formalin) and the rapid physiological decay of fruit remain persistent food-safety and economic problems within agricultural supply chains. Deep learning offers a non-destructive route to automated fruit-quality screening; however, the literature has largely pursued peak accuracy using progressively heavier network backbones, leaving the computational cost of that accuracy and therefore the feasibility of on-site, embedded deployment insufficiently examined. This study benchmarks three representative visual-recognition paradigms of markedly different scale, namely MobileNetV2 (a depthwise-separable lightweight convolutional neural network), ResNet-50 (a deep residual network), and ViT-B/16 (a patch-based Vision Transformer), on the identical three-class task of distinguishing fresh, rotten, and formalin-mixed fruit. A total of 10,154 images from the public FruitVision dataset were processed under a single fixed preprocessing and training protocol, so that architecture was the only experimental variable. Rather than accuracy alone, performance was assessed through an efficiency lens that normalises accuracy by parameter count and by inference cost (GFLOPs). The lightweight MobileNetV2 attained the highest test accuracy (99.69%) while using approximately one-seventh of the parameters and one-thirteenth of the floating-point operations of ResNet-50, and about one twenty-fifth of the parameters of ViT-B/16; the Transformer recorded the lowest accuracy (99.28%) at the highest cost. These results indicate that, for this medium-scale task, additional architectural capacity yields a negligible accuracy return, and that a compact model can support reliable, safety-critical formalin screening on resource-constrained devices. Per-class reliability and deployment implications, including one residual false negative, are reported without overstatement.
PERANCANGAN SISTEM MONITORING PERKEMBANGAN EDUKASI ANAK USIA DINI BERBASIS WEBSITE MENGGUNAKAN MODEL RAPID APPLICATION DEVELOPMENT (RAD) DAN METODE FUZZY LOGIC PADA TK BINA PERTIWI Muhammad Arief Tri Faturachman; Agus Heri Yunial
Informatika: Jurnal Teknik Informatika dan Multimedia Vol. 6 No. 2 (2026): Oktober : JURNAL TEKNIK INFORMATIKA DAN MULTIMEDIA
Publisher : LPPM Politeknik Pratama Kendal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/informatika.v6i2.1853

Abstract

Monitoring early childhood development is essential to support optimal growth. In many institutions, including TK Bina Pertiwi, manual record-keeping leads to errors, reporting delays, and unstructured archiving. This study designs a web-based monitoring system using the Rapid Application Development model (Requirements Planning, User Design, Construction, Cutover) and evaluates development outcomes with the Mamdani fuzzy logic method using three inputs (cognitive, psychomotor, socio-emotional) to produce outputs of “Needs Stimulation” or “Developing.” The system was implemented with the Laravel framework and MySQL and tested via Black Box and White Box testing. Black Box testing showed that all 15 functional scenarios (100%) ran as expected, while White Box testing of 10 core modules produced cyclomatic complexity values V(G) of 1-4, indicating a well-structured, low-risk program flow. A user acceptance questionnaire completed by 12 respondents further yielded a feasibility score of 94%. Results indicate the system replaces manual records, speeds up reporting, and provides centralized data access for Admin, Principal, Teachers, and Parents, thereby making monitoring coordination more effective.
PENGEMBANGAN APLIKASI OPTIMASI PERENCANAAN BAHAN BAKU MENU MAKANAN MENGGUNAKAN LINEAR PROGRAMMING BERBASIS WEB Syahrul Ramadhan; Agus Heri Yunial
Computing and Education Technology Journal Vol 6, No 2 (2026): OKTOBER
Publisher : Pendidikan Komputer FKIP Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/cetj.v6i2.20093

Abstract

Perencanaan kebutuhan bahan baku pada praktik Tata Boga di SMKN 7 Tangerang Selatan masih dilakukan secara manual sehingga berpotensi menyebabkan kesalahan perhitungan, kekurangan, maupun kelebihan bahan baku. Penelitian ini bertujuan merancang dan mengembangkan aplikasi berbasis web untuk membantu perencanaan dan perhitungan kebutuhan bahan baku secara otomatis serta menerapkan Linear Programming untuk menentukan kapasitas produksi maksimum dan jumlah paket menu optimal berdasarkan ketersediaan bahan baku. Metode penelitian yang digunakan adalah Research and Development (R&D) untuk menghasilkan dan menguji aplikasi yang dikembangkan. Implementasi Linear Programming dilakukan dalam 2 mode, yaitu Mode Single untuk menentukan kapasitas produksi maksimum satu menu dan Mode Multi menggunakan metode Simplex untuk menentukan jumlah paket menu optimal beberapa menu dalam satu paket. Pengujian sistem dilakukan menggunakan Black Box, White Box, dan User Acceptance Test (UAT). Hasil Mode Single pada menu Ayam Goreng Bawang Putih menunjukkan kapasitas produksi maksimum sebesar 160 porsi berdasarkan keterbatasan stok. Pada Mode Multi, sistem menghasilkan 15 paket menu dengan kombinasi Ayam Goreng Bawang Putih, Tahu Isi Sayur, Soto Ayam, dan Bubur Sumsum masing-masing sebanyak 15 porsi. Sistem juga menampilkan slack, binding constraint, dan bottleneck sebagai informasi hasil optimasi. Pengujian White Box menghasilkan nilai Cyclomatic Complexity sebesar 3 dengan tiga independent path yang berhasil diuji. Hasil UAT memperoleh persentase sebesar 85,5% dan termasuk kategori Sangat Baik. Pengguna menilai aplikasi membantu perencanaan. Kebaruan penelitian ini terletak pada integrasi Linear Programming dengan data resep, jumlah porsi, dan stok bahan baku dalam aplikasi berbasis web untuk mendukung perencanaan bahan baku praktik Tata Boga di sekolah kejuruan.
Co-Authors A. Nurul Anwar Achmad Lutfi Fuadi Ade Napila Ahmad Fauzi Andrian Hidayat Azriel Akbar Dinar Dede Eko Saputro Dennis Eka Putra Joko Suwarno Muhammad Arief Tri Faturachman Reza Saputra Syahrul R, Syahrul Willis Puspita Sari