Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal Jurnal Sistim Informasi dan Teknologi AKADEMIK: Jurnal Mahasiswa Humanis TECHSI - Jurnal Teknik Informatika
Putra, Rafi Septiawan
Unknown Affiliation
Religion Humanities Computer Science & IT Decision Sciences, Operations Research & Management Education Social Sciences Other

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Sistem Pakar dalam Menganalisis Gangguan Jiwa Menggunakan Metode Certainty Factor Putra, Rafi Septiawan; Yuhandri, Y
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 4 (Accepted)
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/jsisfotek.v3i4.177

Abstract

People with Mental Disorders (ODGJ) as a trigger for people who suffer from disorders of thought, feeling and behavior cause changes in attitudes and behavior that hinder normal human functioning. Mental disorders as a syndrome characterized by a change in a person's behavior that will be associated with symptoms such as difficulties or disorders, as well as psychological functions and behavior that are not confident in dealing with people but can also be with that person. An expert system is an intelligent computer technology that is based on solving problems using inferential knowledge and procedures. As a problem solver, expert systems will also find it easier to make decisions or policies like humans do. This study aims to produce an expert system that is used to analyze mental disorders who can make similar decisions, as well as psychiatric specialists. The data processed in this study is scientific data on mental disorders ranging from types of mental illness, early symptoms of disease and patient diagnosis data by mental health specialists, then the data is processed using the Certainty Factor method and displayed in the form of a web-based application using the PHP programming language. and MySQL databases. The results obtained from testing the expert system using the Certainty Factor method show that there is a match between the results of an expert diagnosis of depression with a certainty level of 73%. An expert system for analyzing mental disorders using the Certainty Factor method can make it easier for sufferers to understand the type of mental disorder they are experiencing.
Kajian Penerapan Teknologi Informatika pada Dunia Kesehatan Putra, Rafi Septiawan
AKADEMIK: Jurnal Mahasiswa Humanis Vol. 3 No. 3 (2023): AKADEMIK: Jurnal Mahasiswa Humanis
Publisher : Perhimpunan Sarjana Ekonomi dan Bisnis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37481/jmh.v3i3.813

Abstract

The purpose of this research is to study the application of information technology to the world of health. Research methods This research uses qualitative approaches and library methods, both involving collection of library data through reading, recording, and processing research materials. Telenursing results actually make it much easier to access health care for under-serviced populations, like monitoring services at home or individuals with chronic health problems. However, this technology is still not optimally used in Indonesia. After reading the description above, it can be concluded that, in cases where patients are unlikely to obtain health services or nursing directly, either for remote reasons or because they want to save and efficiently save their time during the trip, the telenursing service is one of the options that can be used.
PENERAPAN ALGORITMA A* UNTUK MENETUKAN JALUR TERPENDEK DARI SIPIROK KE UIN SYAHADA PADANGSIDIMPUAN: Indonesia Linhar, Ade; Putra, Rafi Septiawan; Simbolon, Hasanal Fachri Satia; Izhari, Fahmi; Sipahutar, Meri Nova Marito
TECHSI - Jurnal Teknik Informatika Vol. 16 No. 2 (2025)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v16i2.25797

Abstract

Efisiensi mobilitas antara pusat pemerintahan Kabupaten Tapanuli Selatan di Sipirok dengan pusat pendidikan UIN Syahada Padangsidimpuan menjadi krusial seiring peningkatan aktivitas akademik dan administrasi. Penelitian ini bertujuan untuk menerapkan dan menganalisis kinerja algoritma A* (A-Star) dalam menentukan jalur terpendek pada rute tersebut. Berbeda dengan algoritma Dijkstra yang menelusuri seluruh kemungkinan rute, algoritma A* memanfaatkan fungsi heuristik untuk memprioritaskan pencarian jalur yang lebih menjanjikan menuju tujuan. Penelitian ini memodelkan peta jalan lintas Sipirok-Padangsidimpuan ke dalam bentuk graf berbobot, di mana simpul merepresentasikan persimpangan atau landmark utama. Fungsi heuristik yang digunakan adalah Haversine Formula untuk menghitung jarak garis lurus berdasarkan koordinat geografis. Hasil perhitungan menunjukkan bahwa algoritma A* sukses menemukan rute optimal dengan jarak tempuh total ±38 km melalui Jalan Lintas Sumatera. Analisis kompleksitas menunjukkan bahwa A* memiliki waktu pencarian yang lebih cepat (node visit lebih sedikit) dibandingkan pencarian buta (blind search), menjadikannya solusi efektif untuk sistem navigasi lokal di wilayah Tapanuli Selatan.
Episodic Sparse Cost Evaluation for Policy Analysis in Stochastic Shortest Path Problems: english Izhari, Fahmi; Putra, Rafi Septiawan; Simbolon, Hasanal Fachri Satia; Linhar, Ade
TECHSI - Jurnal Teknik Informatika Vol. 16 No. 2 (2025)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v16i2.25800

Abstract

Conventional evaluations of stochastic shortest path policies typically rely on dense reward or cost signals, which often obscure rare but behaviorally critical interactions. This paper introduces an episodic sparse-cost evaluation framework that assigns costs only to a small subset of state action pairs identified through a short probing phase, thereby decoupling cost accumulation from trajectory length. The objective of this study is to assess whether episodic sparse costs can provide a more interpretable and behavior-focused evaluation of policy execution compared to dense formulations. The framework is empirically validated through controlled navigation experiments under a fixed policy in a grid-based stochastic shortest path setting. In a representative episode, the agent successfully reached the terminal state in 95 steps, while incurring only two cost-triggering events drawn from a sparse support set of size five. This resulted in a total episodic cost of 2.0 and a hit rate of 0.021, indicating that more than 97% of agent environment interactions were cost-free. The temporal distribution of costs appeared as isolated impulses rather than continuous signals, enabling precise localization of critical decision points along the trajectory. These findings demonstrate that episodic sparse-cost evaluation yields bounded, event driven cost behavior that remains stable even for long trajectories. The proposed framework offers a transparent and scalable alternative for analyzing policy behavior in stochastic environments, particularly in scenarios where rare violations, constraints, or risk sensitive interactions are of primary concern. Future research will extend this evaluation paradigm to multi-episode analysis, adaptive policies, and integration with constraint aware learning objectives.
Analisis Komparasi Algoritma Random Forest dan Support Vector Machine untuk Deteksi Intrusi Jaringan Fachri Satia Simbolon, Hasanal; Linhar P, Ade; Putra, Rafi Septiawan; Izhari, Fahmi
TECHSI - Jurnal Teknik Informatika Vol. 16 No. 2 (2025)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v16i2.25811

Abstract

Meningkatnya kompleksitas serangan siber menuntut adanya sistem keamanan jaringan yang adaptif dan efisien. Intrusion Detection System (IDS) tradisional seringkali memiliki keterbatasan dalam mengenali pola serangan baru. Penelitian ini bertujuan untuk mengevaluasi kinerja dua algoritma Machine Learning, yaitu Random Forest (RF) dan Support Vector Machine (SVM), dalam mengklasifikasikan trafik jaringan normal dan serangan. Eksperimen dilakukan menggunakan dataset NSL-KDD dengan melibatkan seluruh 41 fitur melalui tahapan preprocessing, normalisasi, dan validasi data dengan rasio 80:20. Hasil pengujian menunjukkan bahwa algoritma Random Forest mengungguli SVM dengan tingkat akurasi mencapai 99.78%, presisi 1.00, dan recall 1.00. Sebaliknya, SVM mencatatkan akurasi sebesar 99.03%. Selain unggul dalam akurasi, Random Forest terbukti lebih efisien dengan waktu pelatihan (training time) rata-rata 3.72 detik, hampir dua kali lebih cepat dibandingkan SVM yang membutuhkan 6.61 detik. Berdasarkan hasil tersebut, Random Forest direkomendasikan sebagai algoritma yang lebih efektif untuk implementasi IDS pada lingkungan yang membutuhkan respons waktu nyata (real-time).
Co-Authors Fachri Satia Simbolon, Hasanal Izhari, Fahmi Linhar P, Ade Linhar, Ade Simbolon, Hasanal Fachri Satia Sipahutar, Meri Nova Marito Yuhandri Yuhandri, Yuhandri