Article Per Year (5 Year)
p-Index From 2021 - 2026
1.006
P-Index
This Author published in this journals
All Journal INTECOMS: Journal of Information Technology and Computer Science Journal of Innovation and Future Technology (IFTECH) Jurnal Teknologi Informatika dan Komputer Jurnal Hasil Pengabdian Masyarakat (JURIBMAS) OKTAL : Jurnal Ilmu Komputer dan Sains
Ahmad Musyafa
Universitas Pamulang
Astronomy Chemistry Computer Science & IT Education Electrical & Electronics Engineering Engineering Library & Information Science Social Sciences

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
ANALISIS DAN EVALUASI KINERJA CHATBOT PENERIMAAN MAHASISWA BARU BERBASIS LLM DENGAN PENDEKATAN RAG Daerobby; Tukiyat; Ahmad Musyafa
Journal of Innovation And Future Technology Vol. 8 No. 1 (2026): Vol 8 No 1 (Februari 2026): Journal of Innovation and Future Technology (IFTECH
Publisher : LPPM Unbaja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/iftech.v8i1.4452

Abstract

The advancement of artificial intelligence has driven LLM-based chatbot implementation in education, particularly for New Student Admission (PMB) services. This research analyzes and evaluates an LLM-based PMB chatbot using Retrieval-Augmented Generation (RAG) at Politeknik Krakatau. The system integrates three LLM models (GPT-4 Turbo, Mistral Devstral, Xiaomi Mimo-v2) with FAISS and LangChain. Comprehensive evaluation uses eight standard metrics: four for retrieval (Recall@3, Precision@3, MRR, NDCG@3) and four for generation (BERTScore, ROUGE-1, ROUGE-L, METEOR), with 100 questions across six categories. Results show the retrieval component achieves excellent performance with Recall@3 of 1.000 (perfect), MRR of 0.756, and NDCG@3 of 0.864, indicating effective document finding and ranking. For generation, Mistral Devstral demonstrates best performance with BERTScore of 0.755, ROUGE-1 of 0.604, and METEOR of 0.427, followed by GPT-4 Turbo (BERTScore 0.723) and Xiaomi Mimo-v2 (BERTScore 0.718). These comprehensive results enable evidence-based model selection, producing a chatbot delivering accurate, contextually relevant, and consistent responses to prospective students. This directly addresses slow and inefficient admission services by reducing administrative workload through automated, high-quality information provision while improving response speed and reliability. Compared to previous studies, this research provides the most comprehensive evaluation of RAG-based PMB chatbots in Indonesia, with retrieval performance surpassing prior studies and offering actionable insights bridging technical metrics and real-world service improvement in higher education institutions.
DAPATKAH MODEL TRANSFORMER MENDETEKSI TOKEN SCAM? SEBUAH STUDI PADA SMART CONTRACT ERC-20 Andhi Saputro; Makhsun Makhsun; Ahmad Musyafa
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 2 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/h46hgh88

Abstract

Pertumbuhan pesat ekosistem blockchain telah melahirkan ribuan token pada jaringan ERC-20. Fenomena ini mendorong inovasi finansial, namun sekaligus meningkatkan risiko penipuan melalui smart contract yang menyembunyikan mekanisme berbahaya seperti backdoor, blacklist bot, dan manipulasi fee. Penelitian ini mengusulkan pendekatan klasifikasi berbasis Transformer secara end-to-end untuk mendeteksi token scam ERC-20 menggunakan kode sumber Solidity sebagai satu-satunya fitur masukan. Tiga model dievaluasi: CodeBERT (microsoft/codebert-base), RoBERTa (roberta-base), dan GraphCodeBERT (microsoft/graphcodebert-base). Dataset terdiri dari 60.000 kontrak ERC-20 yang diambil dari repositori ASSERT-KTH/DISL, dengan 30.000 kontrak dilabeli secara semi-otomatis menggunakan analisis kode statis berbasis aturan (rule-based) untuk tujuh jenis scam: Honeypot, High Tax, Balance Manipulation, Blacklist, Hidden Owner, Rug Pull, dan Unlimited Mint. Pada klasifikasi biner, GraphCodeBERT mencapai performa terbaik dengan F1-Score 0,9295 dan AUC 0,9808. Pada klasifikasi multilabel, RoBERTa unggul pada F1-Score (0,8681) sementara GraphCodeBERT unggul pada AUC (0,9672). Label Blacklist menjadi tantangan tersendiri dengan F1-Score hanya 0,61–0,64 akibat ketidakseimbangan kelas yang ekstrem. Hasil penelitian membuktikan bahwa representasi kode sumber Solidity melalui model Transformer sudah cukup informatif untuk membedakan kontrak scam dari kontrak legitim secara otomatis.
ANALISIS PERILAKU BELAJAR SISWA DI ERA ARTIFICIAL INTELLIGENCE MENGGUNAKAN MODEL DEEP LEARNING TABNET DAN TABTRANSFORMER UNTUK PENGEMBANGAN REKOMENDASI STRATEGI PEMBELAJARAN Ahmad Muhammad; Ahmad Musyafa; Tukiyat Tukiyat
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 2 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/t0adps90

Abstract

Perkembangan teknologi kecerdasan artifisial (Artificial Intelligence/AI) telah membawa perubahan signifikan terhadap perilaku belajar siswa, terutama dalam cara siswa mengakses informasi, menyelesaikan tugas, dan membangun strategi belajar mandiri. Penelitian ini bertujuan untuk menganalisis perilaku belajar siswa di era AI menggunakan model deep learning TabNet dan TabTransformer untuk memprediksi capaian akademik siswa serta mengembangkan rekomendasi strategi pembelajaran yang adaptif. Penelitian menggunakan pendekatan kuantitatif dengan data tabular yang diperoleh dari 2.052 siswa SMA Plus PGRI Cibinong. Variabel penelitian mencakup aspek akademik, digital, psikologis, sosial, dan penggunaan AI dalam pembelajaran. Tahapan penelitian meliputi preprocessing data, encoding, pembagian data latih dan data uji, pemodelan menggunakan TabNet dan TabTransformer, evaluasi model menggunakan RMSE, MAE, dan R², serta analisis feature importance untuk segmentasi siswa. Hasil penelitian menunjukkan bahwa TabTransformer memiliki performa lebih baik dibandingkan TabNet dalam memodelkan hubungan antara perilaku belajar dan nilai akademik siswa. Variabel usaha belajar, penggunaan AI untuk memahami materi, dan motivasi belajar menjadi faktor dominan yang memengaruhi capaian akademik. Selain itu, penelitian menghasilkan empat segmentasi profil siswa yang digunakan sebagai dasar penyusunan rekomendasi strategi pembelajaran adaptif. Penelitian ini menunjukkan bahwa AI berperan sebagai faktor pendukung pembelajaran, sementara regulasi diri dan usaha belajar tetap menjadi faktor utama keberhasilan akademik siswa.
Inspiring Future: Motivational Program for Visually Impaired Students toward Higher Education in Information Technology at Malaysian Association for the Blind (MAB) Ahmad Musyafa; Lisda Fitriana Masitoh; Joko Riyano; Nani Rusnaeni; Teti Desyani; Okta Irawati; Zurnan Alfian
JURIBMAS : Jurnal Hasil Pengabdian Masyarakat Vol 5 No 1 (2026): Juli 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juribmas.v5i1.1172

Abstract

Inclusive education is a crucial effort to ensure equitable access to education for all, including those with visual impairments. Although technological advances have made learning easier for visually impaired students, challenges remain that affect their motivation to pursue higher education. Limited information, low self-confidence, and stigma regarding the academic abilities of people with visually impaired are some of the frequently encountered barriers. This international community service program aims to increase the motivation, self-confidence, and insight of visually impaired students regarding higher education opportunities, particularly in the fields of information technology and computer engineering. The program was held on May 18, 2026, at the Malaysian Association for the Blind (MAB) in Kuala Lumpur, Malaysia, and involved 12 visually impaired students. The program included the delivery of motivational materials, an introduction to inclusive higher education, reinforcement of simple logic and mathematics, and interactive discussions. The program demonstrated high levels of enthusiasm among participants. Participants gained new insights into opportunities for continuing higher education, support for inclusive campuses, and the use of assistive technology in the learning process. This activity positively impacted participants' motivation and confidence to pursue higher education. Furthermore, it strengthened the role of higher education institutions in supporting inclusive education and equitable access to education for visually impaired students.
A Comparative Study of DenseNet-201 and Swin Transformer for Malignant and Benign Skin Lesion Classification Dahlan Hidayat; Ahmad Musyafa; Murni Handayani
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3265

Abstract

Skin cancer has a high global prevalence, underscoring the need for accurate and efficient early detection systems to support screening. This study presents a comparative analysis of DenseNet-201 and Swin Transformer for binary classification of malignant and benign skin lesions using the BCN20000 dataset, which contains 12,413 dermoscopic images. The proposed workflow includes image preprocessing and augmentation, transfer learning-based model training, and evaluation under a 5-fold stratified cross-validation protocol. Performance is assessed using Accuracy, Precision, Sensitivity (Recall), F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). In addition, computational efficiency is examined in terms of parameter count, model size, and training time. Across five folds, DenseNet-201 achieved 88.05% Accuracy, 88.90% Precision, 89.48% Sensitivity, 89.17% F1-score, and 94.73% AUC, whereas Swin Transformer achieved 87.42% Accuracy, 89.77% Precision, 87.06% Sensitivity, 88.39% F1-score, and 94.33% AUC. A paired t-test at α = 0.05 indicated no statistically significant performance difference between the two models. Model interpretability was investigated using Grad-CAM for DenseNet-201 and EigenCAM for Swin Transformer to verify that predictions were driven by lesion-relevant regions. Overall, the results suggest that both architectures are suitable candidates for dermoscopic image-based skin lesion screening support systems, including teledermatology applications.
Implementasi IoT Menggunakan Mikrokontroler NodeMCU ESP8266 Dalam Mengotomatisasi Mesin Untuk Penampungan Air Jaka Sutresna; Fitri Yanti; Ahmad Musyafa
OKTAL : Jurnal Ilmu Komputer dan Sains Vol 4 No 08 (2025): OKTAL : Jurnal Ilmu Komputer Dan Sains
Publisher : CV. Multi Kreasi Media

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

Abstract

The rapid development of Internet of Things (IoT) technology provides significant opportunities for creating intelligent, efficient, and adaptive automation systems, especially for domestic applications. One of these implementations includes automated water storage management and remote control of household electrical devices such as lighting systems. This research aims to design and implement a web-based automatic water tank control and lighting management system utilizing the NodeMCU ESP8266 microcontroller and ultrasonic sensors (HC-SR04). The ultrasonic sensor accurately measures the real-time water level inside the tank. Meanwhile, NodeMCU ESP8266 functions as a central controller that processes sensor data and establishes Wi-Fi connectivity for communication with a web platform developed using the XAMPP server, PHP, and MySQL. The designed system employs a hybrid operation mode combining automatic pump control based on sensor readings and manual lighting control through a responsive web interface. The testing results demonstrate that the system operates with high accuracy, exhibiting a sensor measurement error of approximately ±2 cm and system response times of less than 1 second. Additionally, testing of the communication stability between NodeMCU and the web platform indicated reliable and consistent connectivity without significant interruptions. The developed system offers ease of management, effective energy and water efficiency, and aligns with an innovative, adaptive, and flexible smart living concept suitable for various scenarios in modern household environments.
Co-Authors Ahmad Muhammad Andhi Saputro Daerobby Dahlan Hidayat Fitri Yanti Jaka Sutresna Joko Riyano Lisda Fitriana Masitoh Makhsun Makhsun Murni Handayani Nani Rusnaeni Okta Irawati Teti Desyani Tukiyat Tukiyat Tukiyat Zurnan Alfian