Article Per Year (5 Year)
p-Index From 2021 - 2026
1.463
P-Index
This Author published in this journals
All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Sinkron : Jurnal dan Penelitian Teknik Informatika Data Science: Journal of Computing and Applied Informatics Journal of Information Systems and Informatics JTIK (Jurnal Teknik Informatika Kaputama) Jurnal Sistem Komputer dan Informatika (JSON) Journal of Applied Data Sciences
Mohammad Andri Budiman
Jurusan Ilmu Komputer Fakultas Ilmu Komputer Dan Teknologi Informasi, USU
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
Reducing Semantic Distortion of Multiword Expressions for Topic Modeling with Latent Dirichlet Allocation Sitopu, Widya Astuti; Nababan, Erna Budhiarti; Budiman, Mohammad Andri
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1266

Abstract

The Makan Bergizi Gratis (MBG) is one of the Indonesian government’s priority initiatives that has received significant coverage in online media. To understand the main themes within these narratives, this study applies topic modeling using Latent Dirichlet Allocation (LDA). However, the results of topic modeling are highly influenced by the preprocessing stage, particularly in handling multiword expressions (MWEs) such as named entities, collocations, and compound words. This study compares two preprocessing approaches: basic and extended, with the latter involving the masking of MWEs. Experimental results show that the extended preprocessing model achieved the highest coherence score of 0.5149 at K=22K = 22K=22, with four other scores also exceeding 0.496, whereas the basic preprocessing model only reached a maximum of 0.3932 at K=10K = 10K=10. Furthermore, cosine similarity scores between topics in the extended model were lower (maximum 0.7406) than in the basic model (maximum 0.8244), indicating that the topics produced were more diverse and less overlapping. These findings highlight the importance of preprocessing strategies that preserve phrase-level meaning to reduce semantic distortion and improve topic coherence and representation-particularly in analyzing media discourse on public policy programs such as MBG.
Perbandingan Algoritma Greedy dan Hill Climbing Untuk Menentukan Fasilitas Kesehatan Tingkat Pertama (FKTP) Terdekat Bagi Peserta BPJS Kesehatan Fithaloka, Dhea; Budiman, Mohammad Andri; Rachmawati, Dian
JTIK (Jurnal Teknik Informatika Kaputama) Vol. 1 No. 2 (2017): Volume 1, Nomor 2, Juli 2017
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59697/jtik.v1i2.579

Abstract

Kebutuhan pencarian Fasilitas Kesehatan Tingkat Pertama di Kota Medan termasuk cukup besar, dimana Fasilitas Kesehatan Tingkat Pertama melayani sesuai keluhan pasien, seperti penyakit umum, rawat jalan dan rawat inap, konsultasi, obat-obat dan lain sebagainya. Terdapat pilihan wilayah yang dapat ditempuh untuk menuju Fasilitas Kesehatan Tingkat Pertama terdekat yang diinginkan, terdapat 21 wilayah Fasilitas Kesehatan Tingkat Pertama di kota medan. Dalam pencarian Fasilitas Kesehatan Tingkat Pertama terdekat di Kota Medan tersebut akan diterapkan kedalam sebuah graf. Dalam menyelesaikan graf diperlukan pula algoritma, algoritma yang akan digunakan yaitu algoritma Hill Climbing dan algoritma Greedy, dimana algoritma Hill Climbing adalah suatu metode untuk mencari dan menentukan rute yang paling singkat dengan memperkecil tempat yang disinggahi dengan menggunakan cara heuristic dan algoritma Greedy memberikan solusi memecahkan masalah dengan membuat pilihan optimum lokal. Berdasarkan Hasil pencarian Fasilitas Kesehatan Tingkat Pertama di Kota Medan dengan menggunakan algoritma Hill Climbing dan algoritma Greedy menunjukkan hasil yang berbeda dan running time yang berbeda dimana algoritma Hill Climbing memiliki nilai running time yang lebih cepat serta menunjukkan hasil yang sesuai dengan tujuan dibandingkan algoritma Greedy.
PERBANDINGAN ALGORITMA MESSAGE DIGEST-5 (MD5) DAN GOSUDARSTVENNYI STANDARD (GOST) PADA HASHING FILE DOKUMEN Benedict, Marthin; Budiman, Mohammad Andri; Rachmawati, Dian
JTIK (Jurnal Teknik Informatika Kaputama) Vol. 1 No. 1 (2017): Volume 1, Nomor 1, Januari 2017
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59697/jtik.v1i1.686

Abstract

Dokumen elektronik memiliki sifat terbuka, artinya isi dokumen dapat dibaca dan diubah dengan mudah oleh pihak-pihak yang tidak berhak. Hal tersebut menyebabkan integritas dokumen menjadi tidak terjamin. Integritas dokumen elektronik dapat dijamin dengan menggunakan teknik kriptografi, salah satunya hash function. Ada banyak algoritma yang dapat digunakan untuk hashing file atau dokumen, dua algoritma diantaranya adalah algoritma Message Digest-5 (MD5) dan algoritma Gosudarstvennyi Standard (GOST). Secara garis besar, kedua algoritma mengambil panjang isi file atau pesan dalam bit lalu dibagi menjadi blok-blok bit setelah itu pada setiap blok akan dilakukan operasi matematika sehingga menghasilkan 128 bit nilai hash pada Message Digest-5 (MD5) dan 256 bit nilai hash pada Gosudarstvennyi Standard (GOST). Setelah itu, nilai hash diubah dalam bentuk heksadesimal sehingga Message Digest-5 (MD5) akan menghasilkan 32 karakter heksadesimal nilai hash dan 64 karakter heksadesimal nilai hash pada Gosudarstvennyi Standard (GOST).
Diffusion2D and Anchored Inference for Asymptotic Stabilization of Diffusion-Convolutional Neural Networks in Multidomain Medical Image Classification Hanna Willa Dhany; Sutarman Sutarman; Poltak Sihombing; Mohammad Andri Budiman
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1215

Abstract

Medical image classification across heterogeneous domains remains challenging due to domain shift, spatial variability, and unstable inference behavior. This study proposes a diffusion-stabilized Diffusion-Convolutional Neural Network (DCNN) framework that integrates Diffusion2D and post-hoc Anchored Diffusion to improve inference stability, probabilistic consistency, and robustness in multidomain medical image classification. The main contribution of this work is the introduction of a two-stage stabilization mechanism in which Diffusion2D performs controlled intra-image diffusion on feature representations before graph construction, while Anchored Diffusion refines uncertain predictions in the logit space through a k-nearest neighbors graph without retraining. The framework was evaluated on heterogeneous medical imaging datasets consisting of brain MRI, leukemia microscopy, and COVID-19 chest radiographs. Experimental results show that the proposed approach maintained baseline classification performance with an accuracy of 64.70% while improving the Macro-F1 score from 0.7045 to 0.7061. The diffusion mechanism reduced the average Laplacian value from 0.864355 to 0.187525, corresponding to a 78.23% reduction in spatial gradient variability. Internal analysis further demonstrated stable diffusion coefficients with a mean value of 0.141734 and a standard deviation of 0.003757, indicating controlled diffusion behavior. Anchored Diffusion selectively refined uncertain predictions, affecting only 0.6% of evaluated samples while preserving overall decision consistency. Repeated inference experiments across 40 iterations also revealed highly stable confidence trajectories with no observable variance after diffusion stabilization. The novelty of this research lies in combining feature-level diffusion stabilization, post-hoc anchored inference, and asymptotic regularization within a unified DCNN framework, providing a theoretically grounded and uncertainty-aware approach for robust multidomain medical image classification.
Co-Authors Amalia Amalia Amer Sharif, Amer Benedict, Marthin Budi Satria Muchlis, Budi Satria Dhea Fithaloka Dian Rachmawati Dian Rachmawati Efendi, Syahril Erna Budhiarti Nababan Fithaloka, Dhea Ginting, Cindy Laurent Handrizal Hanna Willa Dhany Hidayati, Indri Imanuel Zega Karina Lolo Manik Muhammad Safri Lubis Muhammad Yogi Saputra Muhammad Zarlis Muhammad Zarlis, Muhammad Nur Hayati Poltak Sihombing Santoso, Zikri Akmal Sarumaha, Demonius Sawaluddin Nasution Sitopu, Widya Astuti Sutarman Sutarman W, Joceline Schellenberg