Claim Missing Document
Check
Articles

Found 6 Documents
Search

Wood Texture Detection with Conjugate Gradient Neural Network Algorithm Setyawan Widyarto; I Nyoman Suryasa; Otto Fajarianto; Mohd Shafry Mohd Rahim; Khairul Annuar bin Abdullah; Gigih Priyandoko; Gilang Anggit Budaya
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 4: EECSI 2017
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (449.336 KB) | DOI: 10.11591/eecsi.v4.1042

Abstract

This project explored fundamental methods to find the factors that can be used in classifying and detecting the type of wood. Whereas, the literatures have been reviewed to determine the algorithms developed. Some experiments have been conducted to analyze the model and system. The experiments are based on artificial neural network (ANN) algorithm that used back propagation and conjugate gradient method of training function in the process of identification. The experiments carried out to be more accurate than the ANN system, the result is about 96% accuracy. It is expected the method can be used and applied for the detection of the type and classification of wood in the industrial sector, especially agriculture
Development of Web-Based Network Automation Applications Using the Kano Method and Paramiko Library to Simplify the Configuration of Multivendor Network Devices at PT. Digital Vision Nusantara Andi Andara; Setyawan Widyarto; Rusdah
International Journal of Science and Society Vol 5 No 5 (2023): International Journal of Science and Society (IJSOC)
Publisher : GoAcademica Research & Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54783/ijsoc.v5i5.965

Abstract

Computer network is never separated with configuration which is the main task which has to be done in order to make it work. As we know, to configure some devices either server, switch, or router has several methods if we understand how we communicate with the system. Configuration on routers and switches is currently still conventionally done, which means that to configure routers or switches one by one. This is very inefficient, because if the routers and switches that you want to configure are carried out in hundreds or many routers, then the time required by a network administrator is very long. Therefore, network automation is needed which is a solution to perform these complex and repetitive tasks. This automation can help network administrators to configure networks with many devices at once and minimize errors that occur when configuring in a short time. Repetitive work such as configuration backups, configuration restores, and others can be automated. In this project create a web-based network administration automation application. For application development using the Kano method to identify application requirements, design, build and implement applications, this application utilizes the main library, namely paramiko as a liaison and network automation from servers to network devices using the SSHv2 protocol and the Django framework as a Web developers. For the tests carried out on the application using the Black-Box Testing method. The results of this project application can be used as network automation in terms of configuration of network devices such as router configuration, switch configuration, backup and restore configuration centrally so that they can be managed better. This research was conducted with the aim of knowing the category of each feature in a network automation application, the results of this study obtained priority ospf dynamic routing configuration features that entered Must be with a satisfaction level of 0.4285 if implemented and a disappointment level of -0.4285 if this feature not stated, while for the ip address configuration feature, and the On-Dimensional Login feature with a satisfaction level of 0.5713 and a disappointment level of -0.5713 if this feature is implemented, unlike the PIM routing feature configuration feature and the Indifferent configuration verification feature, which for this feature is not often used.
Pengaruh Latihan Continuous Running Terhadap Peningkatan Kebugaran Jasmani Amni, Hazrina; sumaryanti, Sumaryanti; Wulandari, Indri; Widyarto, Setyawan; Agus, Apri; Sukarmin, Yustinus
Jurnal Sporta Saintika Vol 8 No 1 (2023): Jurnal Sporta Saintika Edisi Maret 2023
Publisher : Departemen Kesehatan Dan Rekreasi Fakultas Ilmu Keolahragaan Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/sporta.v8i1.282

Abstract

This study aims to determine the effect of Continuous Running Exercise on Increasing Physical Fitness for S1 students of the Sports Science Study Program, Faculty of Sports Science, Padang State University class of 2021/2022. The research method used in this research is a quasi-experimental method. The population in this study were 215 undergraduate students of the FIK UNP Sports Science Study Program, class of 2021/2022. The sampling technique was carried out by purposive sampling, with a total sample of 20 people. The data collection technique uses a physical fitness test research instrument with a 1600 m rockport run. The results of the study were analyzed statistically using a comparison test (t-test) at a significance level of 5%. The results of this study indicate that the average level of physical fitness of the respondents before being given treatment was (45.30), whereas after being given treatment it was (50.35). There is a significant effect of Continuous Running Exercise on Increasing Physical Fitness of Students of the Sports Science Study Program, Faculty of Sports Science, Padang State Universitywith the results showing the tcount value (4.25) > ttable value (1.73).
Dampak Model Mental Pengguna terhadap Implementasi Multi-Factor Authentication untuk Mitigasi Risiko Password Guessing di Konteks Organisasi Triantoro, Ery; Widyarto, Setyawan
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10290

Abstract

This study conducts a Systematic Literature Review (SLR) to explore the impact of users’ mental models on the implementation of Multi-Factor Authentication (MFA) as a strategy for mitigating password guessing risks in organizational environments. Amid the growing landscape of cyber threats, single-factor authentication has proven to be vulnerable, making MFA an essential layered security solution. However, the adoption of MFA remains slow. Existing studies indicate that expert users perceive MFA as a useful additional layer of verification, whereas non-expert users often view it as a burdensome task (a chore) and may even struggle to distinguish between different types of MFA. Dependence on mobile devices emerges as a common source of frustration for both groups. These findings emphasize that understanding users’ mental models is crucial for improving the implementation and usability of MFA. Innovations such as adaptive MFA or Single Input Multi-Factor Authentication (SIMFA) show potential as solutions to balance security requirements and user experience.
Deep Reinforcement-Driven Clustering and Routing Protocol for Smart Vehicular Networks Riki, Riki; Widyarto, Setyawan
International Journal of Artificial Intelligence Research Vol 9, No 2 (2025): December
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v9i2.1576

Abstract

This study proposes a Deep Reinforcement-Driven Clustering and Routing Protocol (DRCRP) to enhance energy efficiency and routing stability in smart vehicular networks. The protocol integrates an Actor–Critic deep reinforcement learning framework with Proximal Policy Optimization (PPO) to enable adaptive decision-making in dynamic Internet of Vehicles (IoV) environments. Through continuous learning, DRCRP adjusts cluster head selection and routing paths according to real-time vehicular mobility, residual energy, and link quality. Simulation experiments conducted using NS-2 and VanetMobiSim show that DRCRP achieves superior performance compared to benchmark algorithms such as AI-EECR, GWO-CH, and DMCNF. Quantitatively, the proposed model improved the Packet Delivery Ratio (PDR) by up to 4.3%, reduced End-to-End Delay by 18–22%, and lowered Energy Consumption by 12–16%. Moreover, DRCRP effectively minimized communication overhead and extended cluster head and member lifetimes, confirming its ability to balance reliability and energy efficiency. These results demonstrate the capability of reinforcement learning-based architectures to support intelligent, sustainable, and scalable vehicular communication systems under complex mobility conditions
Comparative Analysis of FIFO and LRU Memory Management Algorithms Using CPU-OS Simulator v7.5.50: Kajian Komparatif terhadap Algoritma Manajemen Memori FIFO dan LRU Menggunakan CPU-OS Simulator v7.5.50 Mursid Dwi Hastomo; Setyawan Widyarto
RADIANT: Journal of Applied, Social, and Education Studies Vol. 7 No. 1 (2026): RADIANT: Journal of Applied, Social, and Education Studies
Publisher : Politeknik Assalaam Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52187/rdt.v7i1.378

Abstract

Efficient memory management is a critical aspect of operating system performance, as poor management can lead to high page fault rates, increased execution time, and reduced CPU utilization. This study examines the performance comparison of two widely used memory management strategies, First-In-First-Out (FIFO) and Least Recently Used (LRU), using simulations conducted through the CPU-OS Simulator v7.5.50. The objective is to observe differences in page fault rate, execution time, and CPU efficiency across various scenarios. Three experiments were conducted: first, the impact of cache/pipeline configuration; second, the influence of process scheduling on memory management; and third, the effect of memory size and page access patterns. The results show that LRU tends to provide a lower page fault rate under heavy workloads, while FIFO demonstrates advantages when memory is limited and overhead is minimal. This study contributes to understanding how page replacement algorithms affect system performance in an operating system simulation environment.