cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Sagita Rochman
Contact Email
sagita@unipasby.ac.id
Phone
+6281252569967
Journal Mail Official
jurnalbest@unipasby.ac.id
Editorial Address
Jl. Dukuh Menanggal XII, Surabaya, 60234, Jawa Timur, Indonesia
Location
Kota surabaya,
Jawa timur
INDONESIA
Best : Journal of Applied Electrical, Science and Technology
Published by Universitas PGRI Adi Buana Surabaya
ISSN : 27152871     EISSN : 27145247     DOI : https://doi.org/10.36456/best.vol3.no1
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Physics
A Journal that contain Applied Electrical, Science & Technology. Published twice a year, in March and September. P-ISSN: 2715-2871(print), and E-ISSN: 2714-5247 (online).
Arjuna Subject : Teknik (semua kategori) - Teknik Listrik dan Elektro
Articles 155 Documents
 12   13   14   15   16 
The Development of Train Artificial Intelligence (AI) Model for Bagapit Chess (Catur Bagapit) Engine using Random Forest Regressor Algorithm : a Traditional Game from Kalimantan, Indonesia Hastuti, Dwi; Rosyid, Harits Ar; Arifin, M. Zainal
BEST Vol 8 No 1 (2026): BEST
Publisher : Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/eab74t67

Abstract

Bagapit Chess (Catur Bagapit) is a traditional strategy board game originating from the Kalimantan region of Indonesia. Despite its rich cultural heritage and strategic depth comparable to international Chess, Bagapit Chess remains largely unstudied from a computational intelligence perspective. This paper presents the development of an Artificial Intelligence (AI) model for the Bagapit Chess engine using the Random Forest Regressor (RFR) algorithm. The AI model is trained to evaluate board positions and generate competitive move decisions through a heuristic evaluation function augmented by machine learning. A dataset of 15,000 annotated game positions was constructed from expert gameplay, encoding board features including piece Material Advantage, Chess Movement, Defense Stance, mobility, and Attack Coverage across the 8×8 Bagapit board. The Random Forest Regressor model was integrated with a Negamax search tree enhanced by Alpha-Beta Pruning to achieve efficient and intelligent move selection. The trained model achieved an R² score of 0.9134, a Mean Absolute Error (MAE) of 0.0872, and a Root Mean Squared Error (RMSE) of 0.1104 on the test set. In engine evaluation against a rule-based baseline, the AI model won 84.2% of games under standard time control. This study contributes to the digitalization and preservation of Indonesian traditional games and demonstrates the applicability of ensemble machine learning to non-standard board game engines.
A Systematic Literature Review of Convolutional Neural Networks for Gender Analysis using Fingerprint Images and other Biometric Modalities
BEST Vol 8 No 1 (2026): BEST
Publisher : Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/jhyde786

Abstract

This study systematically reviews the application of Convolutional Neural Networks (CNN) for gender classification using fingerprint images as a biometric identifier. CNN demonstrate a strong ability to automatically extract ridge and texture features that differentiate male and female fingerprints. Using the PRISMA 2020 framework, a Systematic Literature Review (SLR) was conducted on 15 Scopus-indexed studies published between 2020 with 2025, focusing on CNN-based fingerprint gender recognition. The review reveals that CNN models achieved accuracy ranging from 85% to 99.97%, depending on the network architecture, dataset size, and training strategy. Architectures such as VGG16, GoogleLeNet, AlexNet, EfficientNetB0, and Hybrid Model  CNN–LSTM or CNN–SVM performed best, especially when enhanced with data augmentation and transfer learning. Interpretability methods such as Grad-CAM improve model transparency by visualizing fingerprint regions influencing gender prediction. Although the trend in accuracy slightly declined after 2023 due to dataset diversity and overfitting in deeper models, CNN remains the dominant and most reliable approach in biometric analysis.
Performance Analysis of the 110 VDC Battery System in the DC System of the 150 kV Soppeng Substation
BEST Vol 8 No 1 (2026): BEST
Publisher : Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/ct2z2e83

Abstract

Soppeng Substation is an important part of the electrical power transmission system that requires high operational reliability. One of the components that supports this reliability is the 110 VDC battery system, which functions as a backup power source for protection, control, and telecommunication equipment when the AC supply is disrupted. This study aims to analyze the feasibility of the 110 VDC battery system at the Soppeng Substation based on cell voltage, battery bank voltage, charging system performance, and the battery's ability to support DC loads. The research method includes field observations, technical measurements, and analysis of operational data collected from September to November 2025. The results show that the battery bank voltage is 119.4 V for Battery Bank 1 and 123.0 V for Battery Bank 2, with cell voltage deviations of 0.14 V and 0.18 V, respectively, which are still within the allowable limits. The rectifier output voltage ranges from 123.0–123.1 V with a current of about 6.5–6.6 A under float charging conditions. The battery capacity is able to support a DC load of 13.1 A, indicating that the battery system is feasible and reliable as a backup power source.
Design of an Internet of Things (IoT) based Main Reservoir Water Level Measuring Device at Siti Hajar Hospital Sidoarjo Adi Winarno; Rochman, Sagita; Nanda, Bagus
BEST Vol 8 No 1 (2026): BEST
Publisher : Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/zckxkc65

Abstract

The volume of water levels in hospital water reservoirs really requires full monitoring. Where water reservoirs often run out when the water is to be used. This is very fatal and hinders activities that must be carried out immediately. If this happens, it will result in the failure of ongoing activities at the hospital. This research aims to design a prototype that is capable of monitoring water levels in IoT-based hospital reservoirs. By designing a water level monitoring system in the reservoir using the HC-SR04 ultrasonic sensor as an input that measures water level and ESP32 as a microcontroller. The application produced from MIT App Inventor is a notification output and can display monitoring results. Based on the research results, it shows that the water level monitoring system in the reservoir can work well as expected, namely when the water is at the 25% limit, the application will send a notification to the smartphone in the form of sound so that users or technicians can find out and find the cause of the decreasing water level.
Deep Learning Approach for Identifying Fresh and Rotten Chili Peppers using YOLO Sujiwa, Akbar; Hasan, Nailul; Timur, Fajar; Rizkiarna, Reffany C.
BEST Vol 8 No 1 (2026): BEST
Publisher : Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/4gmxqj65

Abstract

Chili peppers are a vital agricultural commodity, yet post-harvest quality assessment primarily relies on manual inspection, which is subjective, labor-intensive, and prone to inconsistency. This study proposes a deep learning-based computer vision system using the You Only Look Once (YOLO) framework to automate the identification and classification of fresh and rotten chili peppers. The model was trained using a dataset of 400 web-crawled images, annotated and augmented to handle visual diversity. A novel evaluation strategy was employed using synthetic image generation to simulate real-world scenarios, including neatly arranged grids and randomly distributed objects with varying orientations. Experimental results demonstrate that the proposed model effectively localizes and classifies chili peppers with confidence scores ranging from 0.55 to 0.90. The system successfully distinguishes between fresh and rotten categories even under conditions of intra-class variation, such as discoloration and shriveling. These findings validate the robustness of the YOLO-based approach, offering a promising, efficient solution for automated post-harvest quality control and smart agriculture applications

Page 16 of 16 | Total Record : 155

 12   13   14   15   16 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol 8 No 1 (2026): BEST Vol 7 No 2 (2025): BEST Vol 7 No 1 (2025): BEST Vol 6 No 2 (2024): BEST (Buana Electrical Science Technology): Journal of Applied Electrical, Scienc Vol 6 No 1 (2024): BEST Vol 5 No 2 (2023): BEST Vol 5 No 1 (2023): BEST Vol 4 No 2 (2022): BEST Vol 4 No 1 (2022): BEST Vol 3 No 2 (2021): BEST Vol 3 No 1 (2021): BEST Vol 2 No 2 (2020): BEST Vol 2 No 1 (2020): BEST Vol 1 No 1 (2019): BEST More Issue