Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal JURNAL TEKNOLOGI DAN OPEN SOURCE Journal of Computer Science, Information Technology and Telecommunication Engineering (JCoSITTE) Informatics and Software Engineering (ISE) Jurnal Komputasi
Atim, Sandi Badiwibowo
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Advanced Encryption Standard (AES) Cryptography Application Design Allwine, Allwine; Atim, Sandi Badiwibowo; Afdhaluddin, Muhammad
Journal of Computer Science, Information Technology and Telecommunication Engineering Vol 6, No 1 (2025)
Publisher : Universitas Muhammadiyah Sumatera Utara, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/jcositte.v6i1.22746

Abstract

As technology advances, the need for secure data transmission and storage increases. Encryption and decryption are essential processes to ensure data confidentiality and integrity. Encryption transforms original data into unreadable form during transmission, while decryption restores it to its original state for the recipient. This guarantees that unauthorized parties cannot access the data. Cryptosystems have evolved over time, and with the rapid growth of communication technologies, stronger standards are needed. AES (Advanced Encryption Standard), based on the Rijndael algorithm, has become the current standard for encryption. AES can encrypt and decrypt 128-bit data blocks with key lengths of 128, 192, or 256 bits, addressing the limitations of older algorithms and providing enhanced data security to protect confidentiality in modern cryptosystems.
Rule-Based Expert System Model with Backward Chaining Algorithm for Symptom-Based Skin Disease Diagnosis Atim, Sandi Badiwibowo; Ibrahim, M. Yhogha Ismail Ibn
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4416

Abstract

A rule-based expert system was a computational model designed to emulate expert decision-making using a knowledge base and inference algorithms. This research developed a rule-based expert system model with a backward chaining algorithm to diagnose skin diseases based on clinical symptoms. Backward chaining, a goal-driven inference method, started with a disease hypothesis (e.g., psoriasis) and verified related symptoms (e.g., kemerahan, sisik keperakan), enabling efficient differentiation of skin diseases with overlapping symptoms, such as dermatitis, psoriasis, and scabies. The model provided advantages in handling uncertainty, produced accurate diagnoses, and supporting interactive symptom verification. Developed using a knowledge base from credible sources like WHO and AAD, the model was intended to assist in clinical decision-making. The results showed that the backward chaining algorithm effectively improved the accuracy and efficiency of diagnosing skin diseases based on patient-reported symptoms
Tier-Aware Entropy-ARAS Approach to Select Microcontroller Boards for Education Sintaro, Sanriomi; Atim, Sandi Badiwibowo; Sabandar, Vederico Pitsalitz
Informatics and Software Engineering Vol. 3 No. 2 (2025): December
Publisher : SAN Scientific

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58777/ise.v3i2.574

Abstract

This study develops a decision support system to recommend microcontroller and IoT learning devices for schools, universities, and training centers under realistic budget constraints while considering both technical capability and educational suitability. The alternatives are grouped into three budget tiers and evaluated using nine criteria covering price, CPU frequency, Flash, RAM/PSRAM, connectivity, usable GPIO, ease of learning, learning resources/community, and local availability/warranty. Objective criterion weights are computed using the Entropy method, and tier-wise rankings are produced using Additive Ratio Assessment (ARAS) through utility scores relative to an ideal alternative. Indicative local price and availability information are compiled from Tokopedia, while qualitative criteria are scored using consistent rubrics to support reproducibility. The results identify ESP32-CAM + baseboard as the top recommendation in Tier 1, LILYGO T-Display S3 in Tier 2, and M5StickC Plus2 in Tier 3; across tiers, Entropy assigns the largest weights to the most discriminative criteria, particularly RAM/PSRAM and, in higher tiers, Flash. The study is limited by market price volatility, approximations in usable GPIO values, and rubric-based qualitative scoring, and it also reflects the tendency of Entropy to concentrate weights on highly dispersed criteria, potentially amplifying outlier advantages. Overall, the proposed tier-aware Entropy–ARAS framework provides a transparent and actionable approach for educational institutions to justify device procurement and usage decisions based on budget, functionality, and learning readiness.
Komparasi Perceptron dan Regresi Logistik pada Klasifikasi Data Breast Cancer Wisconsin Atim, Sandi Badiwibowo; Afdhaluddin, Muhammad
Jurnal Komputasi Vol. 14 No. 1 (2026)
Publisher : Jurusan Ilmu Komputer Fakultas MIPA Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v14i1.340

Abstract

Penelitian ini bertujuan untuk melakukan analisis komparatif terhadap dua model klasifikasi dasar dalam machine learning, yaitu Perceptron klasik dan Regresi Logistik, pada tugas klasifikasi data medis menggunakan dataset Breast Cancer Wisconsin (Diagnostic). Dataset yang digunakan terdiri dari 569 sampel dengan 30 fitur numerik yang merepresentasikan karakteristik morfologi sel kanker hasil biopsi, seperti radius, tekstur, perimeter, area, dan smoothness. Penelitian ini diawali dengan tahap pra-pemrosesan data berupa normalisasi menggunakan metode Min-Max Scaling untuk memastikan setiap fitur berada pada rentang skala yang sama sehingga tidak mendominasi proses pembelajaran model. Selanjutnya, data dibagi menggunakan teknik Hold-Out dengan proporsi 80% sebagai data latih dan 20% sebagai data uji. Proses pelatihan dilakukan pada kedua model dengan parameter standar tanpa optimasi lanjutan untuk menjaga objektivitas perbandingan. Evaluasi kinerja model dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score guna memberikan gambaran menyeluruh terhadap performa klasifikasi, khususnya dalam konteks data medis yang sensitif terhadap kesalahan prediksi. Hasil penelitian menunjukkan bahwa Regresi Logistik memperoleh performa lebih tinggi dengan akurasi sebesar 96,49%, dibandingkan Perceptron klasik yang mencapai 93%. Temuan ini mengindikasikan bahwa pendekatan probabilistik pada Regresi Logistik lebih efektif dalam memodelkan hubungan antar fitur numerik dan menghasilkan batas keputusan yang lebih stabil pada klasifikasi kanker payudara. Kata Kunci: breast cancer; klasifikasi; logistic regression; machine learning; perceptron;
Co-Authors Afdhaluddin, Muhammad Allwine Ibrahim, M. Yhogha Ismail Ibn Sanriomi Sintaro Vederico Pitsalitz Sabandar