cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Eko Prasetyo
Contact Email
jeecs@ubhara.ac.id
Phone
+628819314737
Journal Mail Official
jeecs@ubhara.ac.id
Editorial Address
Faculty of Engineering, Universitas Bhayangkara Surabaya Jl. A. Yani 114, Surabaya
Location
Kota surabaya,
Jawa timur
INDONESIA
JEECS (Journal of Electrical Engineering and Computer Sciences)
Published by Universitas Bhayangkara Surabaya
ISSN : 25280260     EISSN : 25795392     DOI : https://doi.org/10.54732/jeecs
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
We aims to promote high-quality Electrical Engineering and Computer Sciences research among academics and practitioners alike, including power system, electrical engineering, industry automation, mechatronics, computer sciences, informatics, and information system. This journal is dedicated for the author or researcher who has focused in the field of technology and intending on publication and sharing knowledge the novel technology include, but are not limited to, the following topics: Data Mining, Informatics algorithm methodology, Mobile Computing, Automation, Power, Green Technology, Advanced Computer Networks, Image Processing, Computer Vision, Robotics Technology, Decision Support System, Big Data, Data Sciences, Internet of Things, Network Security, Virtual Reality, etc.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 420 Documents
 38   39   40   41   42 
Enhancing OCR Accuracy on Indonesian ID Cards Using Dual-Pipeline Tesseract and Post-Processing Rendy Dwi Reksiyano; Syafrial Fachri Pane; Rolly Maulana Awangga
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.3

Abstract

Manual transcription of data from Indonesian identity cards (KTP) remains prevalent in public institutions, often resulting in inefficiencies and human errors that compromise data accuracy. While Optical Character Recognition (OCR) technologies such as Tesseract have been widely adopted. However, the performance on KTP images is still inconsistent due to non-uniform layouts, low contrast, and background noise. This study proposes a dual-pipeline OCR framework designed to enhance the recognition accuracy of Indonesian KTPs under real-world conditions. First, the pipeline performs static region segmentation based on predefined Regions of Interest (ROI), then uses dynamic keyword heuristics to locate text adaptively across varying layouts. The outputs of both pipelines are merged through a voting and regex-based post-processing mechanism, which includes character normalization and field validation using predefined dictionaries. Experiments were conducted on 78 annotated KTP samples with diverse resolutions and quality of images. Evaluation using Character Error Rate (CER), Word Error Rate (WER), and field-level accuracy metrics resulted in an average CER of 69.82%, WER of 80.20%, and character-level accuracy of 30.18%. Despite moderate performance in free-text areas such as address or occupation, structured fields achieved higher accuracy above 60%. The method runs efficiently in a CPU-only environment without requiring large annotated datasets, demonstrating its suitability for low-resource OCR deployment. Compared to conventional single-pipeline approaches, the proposed framework improves robustness across heterogeneous document layouts and illumination conditions. These findings highlight the potential of lightweight, rule-based OCR systems for practical e-KYC digitization and form a foundation for integrating deep-learning-based layout detection in future research.
Decision Support System for Selecting the Best Restaurant Waiter Using a Combination of WENSLO Weighting and AROMAN Methods Riska Aryanti; Junhai Wang; Agung Deni Wahyudi; Setiawansyah Setiawansyah; Dedi Darwis
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.4

Abstract

The quality of service staff is a key factor in determining business success because they are the front line that interacts directly with consumers. However, performance evaluations of service staff are often still carried out subjectively, based only on the supervisor's perception or brief experiences with customers. This research discusses the application of a decision support system to determine the best restaurant service by combining the Weights by Envelope and Slope (WENSLO) method in criteria weighting and the Alternative Ranking Order Method Accounting for Two-Step Normalization (AROMAN) in the alternative ranking process. The dataset used in this study was collected in 2025 from one of the restaurants in the Lampung area, involving nine waiters as evaluation candidates using six criteria. The six criteria used consist of four benefit criteria: service speed, friendliness, accuracy, and customer satisfaction. The weighting results using the WENSLO method indicate that the order mistakes criterion received the highest weight of 0.7253, followed by completion time with a weight of 0.1700, while the other criteria have relatively small weights. The AROMAN method is used to calculate the final values of alternatives based on the specified weights, resulting in a ranking of restaurant servers. The analysis shows that alternative Waiters KS ranks first with the highest score of 1.6097, followed by Waiters QN and Waiters RB. This finding proves that the combination of the WENSLO and AROMAN methods can produce objective, systematic results, and supports restaurant management in making strategic decisions regarding the selection of the best employees.
SmartNotes Encrypted with Hybrid Cryptography Combining Rivest Cipher 4 and XChaCha20 Elizabeth Piscelia Kusuma; Aqeela Nashwa Naysilla; Bagas Dwi Yulianto
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.5

Abstract

Digital note-taking applications serve as essential tools for personal information management, presenting opportunities for enhanced security mechanisms to protect sensitive data. Most current solutions depend on server-side processing, creating potential vulnerabilities and privacy concerns. However, a robust solution that fully executes hybrid encryption on the client-side to seamlessly protect both text and image data within a single application remains unexplored. This study introduces SmartNotes, a web-based application safeguarding text and image notes through an innovative hybrid encryption system synergistically combining RC4 and XChaCha20 algorithms. A key contribution is the full client-side execution of encryption–decryption processes, eliminating server dependencies and significantly reinforcing data confidentiality. The hybrid design strategically utilizes RC4 for rapid data processing and XChaCha20 for robust cryptographic protection, creating an optimal balance between performance and security.  System performance was rigorously evaluated using seven private datasets under diverse key conditions. Testing methodology included comprehensive assessment of processing speed, data integrity verification, and resistance against unauthorized access attempts. Results demonstrated flawless data restoration across all test cases, validating robustness and reliability. Encryption averaged 1.5 seconds, while decryption required 20.20 seconds metrics well-suited for practical web environments. These findings affirm SmartNotes delivers a secure, autonomous, user-centric solution for digital note management, advancing applied cryptography through a novel client-side hybrid encryption paradigm. This approach successfully balances strong security with practical performance, making it suitable for securing data in everyday web applications.
Development of Augmented Reality-Based English Learning Media for Vocabulary and Pronunciation Said Hirzi Hadi
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.6

Abstract

English learning at the junior high school level often faces challenges in improving vocabulary mastery and pronunciation skills. Previous studies have demonstrated the effectiveness of Augmented Reality (AR) in supporting language learning. However, most of these studies focused only on vocabulary acquisition without integrating pronunciation practice or contextualized 3D object interaction. Therefore, this study aims to develop an AR-based learning medium that visualizes household objects such as refrigerators, microwaves, and scissors, accompanied by their pronunciation sounds. The application was developed using Unity and Vuforia SDK and tested through Black Box Testing and the System Usability Scale (SUS). The test results indicate that the system functions properly and obtained an SUS score of 82.5, categorized as “Excellent.” The developed media is expected to enhance students’ English vocabulary and pronunciation skills through an interactive and enjoyable learning experience that bridges the existing gap in AR-based English learning.
Sentiment Analysis of Public Opinion on PSSI Naturalization Program Based on Social Media Using the Naive Bayes Algorithm Mohammad Reza Fahalevi; Akbar Ilhamsyah; Arifin A. Abd. Karim
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.7

Abstract

Football is the most popular sport in Indonesia and receives tremendous support from the public. However, the player naturalization program initiated by PSSI (the Indonesian Football Association) has become an issue that has captured public attention, generating diverse opinions on social media, particularly on the Twitter platform. This study aims to analyze public sentiment toward the naturalization program by applying the Naïve Bayes classification method. The data used consists of tweets containing keywords related to PSSI naturalization, naturalized players, descendant players, national team naturalization, and overseas players for the national team. The analysis process includes several stages of data preprocessing—such as text cleaning, normalization, and stop word removal—feature extraction using TF-IDF, and sentiment classification using the Naïve Bayes algorithm to categorize opinions into positive, negative, and neutral sentiments. The Naïve Bayes model achieved an accuracy of 0.65, precision of 0.42, recall of 0.65, and an F1-score of 0.51. It performed well in classifying neutral tweets but was less effective in identifying positive and negative sentiments. Overall, the Naïve Bayes method can be utilized for sentiment analysis; however, its classification performance is not yet optimal due to the limited amount of data.
Optimization of Environmentally Friendly Material Selection for Automotive Mechatronics Components Using LCA Data and Multi‑Criteria Decision Making (MCDM) Fauzi Ibrahim; Teuku Marjuni; Rina Febrina; Devi Oktarina; Natalina Natalina; Rani Ismiarti Ergantara; Diah Ayu Wulandari Sulistyaningrum
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.8

Abstract

The automotive industry faces an increasing demand for sustainable material selection as mechatronic components become more widespread in electrified vehicles. However, data-driven material selection approaches that simultaneously integrate environmental, economic, and technical criteria without laboratory experiments remain underdeveloped. This study addresses this gap by developing a computational framework that combines Life Cycle Assessment (LCA) with a Multi-Criteria Decision-Making (MCDM) approach, specifically the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method, using Analytical Hierarchy Process (AHP)–based weights. The framework enables a transparent and reproducible evaluation of environmentally friendly materials for automotive mechatronic components. A case study on an actuator housing evaluates seven material alternatives: Al 6061 (die-cast), recycled Al (die-cast), Mg AZ91 (die-cast), PA6-GF30 (injection), PBT-GF30 (injection), PA12 (SLS 3D print), and bio-based PBT-GF30 (injection). The criteria include total global warming potential (GWP), cumulative energy demand (CED), water use, recyclability, cost, mass, stiffness index, thermal conductivity, and supply risk. Results show that recycled aluminum achieves the highest ranking (closeness coefficient = 0.939), followed by Al 6061 (0.727) and Mg AZ91 (0.547). A Monte Carlo analysis with 1,000 iterations confirms that recycled aluminum consistently remains the best option with 100% robustness under varying weighting conditions. The proposed workflow is replication-ready and can be directly integrated with established LCA databases such as GREET, Ecoinvent, or EPD, enabling engineers to perform sustainable and quantitative material decisions using only data and computational analysis.
Performance Analysis of Electric Bicycles with Planetary BLDC Motors under Different Rider Weights Hegen Persada; Ernando Rizki Dalimunthe; Fika Trisnawati; Novia Utami Putri
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.9

Abstract

Electric bicycles are increasingly used as eco-friendly personal transportation due to their efficiency and low emissions. This study analyzes the effect of rider weight on the energy consumption of a 48V 14Ah lithium-ion battery in an electric bicycle equipped with a 500W planetary BLDC motor. Tests were carried out on three rider weight categories: 60–65 kg, 70–75 kg, and 80–85 kg, to evaluate their impact on current consumption, travel distance, and operating duration. Measurements were taken using a PZEM-015 sensor to monitor voltage, current, and battery capacity in real-time, while speed and distance data were recorded through the Strava application. The results show that as the rider’s weight increases, the average current consumption also rises, decreasing both distance and travel time in a nearly linear pattern. At 60 kg, the bicycle traveled 24.32 km with an average current of 9.52 A, while at 80 kg, the distance decreased to 19.76 km with an average current of 23.15 A. The findings indicate that rider weight significantly affects electric bicycles' performance and energy efficiency. Heavier riders require greater battery power, shorter travel range, and reduced operational efficiency.
Design of IoT-Based Smart Hydroponic Farming with Solar Energy for Sustainable and Precision Crop Production Monika Faswia Fahmi; Deni Tri Laksono; Dedi Tri Laksono
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.10

Abstract

Conventional hydroponic farming systems frequently encounter limitations related to unstable environmental control, suboptimal nutrient management, and strong dependence on grid-based electricity, which collectively hinder their sustainability and scalability, particularly in remote or energy-constrained regions. Recent studies have explored smart hydroponic technologies. However, many remain reliant on external power sources or lack integrated, autonomous control of multiple critical growth parameters. Therefore, this problem reveals a research gap in the development of fully self-powered and intelligent hydroponic systems. This study proposes the design and implementation of a solar-powered, IoT-based smart hydroponic farming system that enables real-time monitoring and closed-loop environmental control. The system integrates multi-sensor measurements, including pH, DS18B20 temperature, total dissolved solids (TDS), and light-dependent resistor (LDR) sensors, coupled with an on–off control strategy to regulate light intensity (115 ADC), water temperature (28 °C), pH (5.5-6.5), and nutrient concentration (840 ppm). A standalone photovoltaic energy subsystem, consisting of a 100 Wp solar panel and a 65 Ah battery, was designed based on a daily energy demand of 378.85 Wh to ensure continuous autonomous operation. Experimental results demonstrate high sensor accuracy, with measurement errors of 0.75% for pH, 0.095% for TDS, and 0.24% for temperature. Moreover, the proposed system effectively stabilizes environmental parameters within predefined setpoints, outperforming uncontrolled conditions. These findings confirm the system’s reliability and potential as a sustainable precision agriculture solution for off-grid hydroponic applications.
A Microcontroller-based Fish Drying System for Enhanced Drying Time with Real-Time Environmental Monitoring Rainiell Guerrero; Armiel Calapit; John Mark Ortega; Ronaldo C. Maaño; Hannah Shamira P. Santonil; Dhon Niño B. Canela; Roselyn A. Maaño; Emelex P. Cortez
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 11 No. 1 (2026): June
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v11i1.1

Abstract

The preservation of fish through drying is a vital practice in coastal regions like the Philippines. Traditional sun-drying methods often suffer from inefficiencies, environmental inconsistencies, and long drying times ranging from 8 to 20 hours. However, existing automated solutions often lack the specific real-time precision required for small-scale costal processing, leading to inconsistent quality. To address these limitations, this study presents the design and implementation of a microcontroller-based fish drying system to enhance drying efficiency through real-time environmental monitoring. The system utilizes an Arduino UNO R3, a DHT22 sensor, infrared heating lamps, and an AC blower fan to maintain a regulated environment between 40°C and 50°C. The microcontroller is the central processing unit, communicating with the sensor to collect real-time temperature and humidity data. This data is used to dynamically control heating elements and ventilation, ensuring optimal drying conditions, reducing drying time, and improving product quality. Experimental results demonstrate that the microcontroller-based system significantly enhances the efficiency and consistency of the drying process to just 3.51 hours compared to conventional methods which recorded 4.48 hours. Technical evaluation through unit and system testing confirmed the system’s reliability in maintaining a 45° indicator. Stakeholders evaluated the prototype using a 5-point scale, resulting in an overall scientific and functional rating of 4.32 (Strongly Agree). This innovation offers a scalable solution for small-scale processors to improve productivity, quality, and production of dried fish products.
Review-Grounded Explainable Recommendation with Faithfulness Evaluation on Amazon Reviews Xiaohan Chang; Yifei Lu; Ziliang Samuel Zhong
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 11 No. 1 (2026): June
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v11i1.2

Abstract

Review text can support explainable recommendations, but many recommender systems still optimize ranking accuracy without providing verifiable textual evidence, or they attach post-hoc explanations whose faithfulness to the model is unclear. This study addresses the lack of a reproducible evaluation setting that jointly measures recommendation quality and whether extracted review evidence actually supports model scoring. We propose Review-Grounded eXplainable Recommender (RGXRec), a lightweight hybrid method that combines interaction signals and TF-IDF review similarity, and we evaluate it on the Luxury Beauty and Video Games subsets of the Amazon Review Data. The pipeline includes rating thresholding, iterative 5-core pruning, chronological leave-one-out splitting, ranked recommendation, extractive evidence generation, and faithfulness evaluation. We compare RGXRec with popularity, metadata-graph KNN, SVD-MF, and ReviewSim using NDCG@K, Recall@K, MRR, evidence coverage, ROUGE-1, sentiment agreement, and a term-attribution faithfulness score. On Luxury Beauty, RGXRec achieves the best ranking performance, reaching NDCG@10 of 0.3606 and outperforming the strongest single-view baseline. On Video Games, collaborative and metadata signals remain stronger for ranking, but RGXRec preserves competitive accuracy while providing non-zero review-grounded faithfulness that interaction-only baselines cannot offer. These findings show that review-grounded recommendation should be evaluated on both ranking quality and explanation faithfulness.

Page 41 of 42 | Total Record : 420

 38   39   40   41   42 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 2 (2026): December Vol. 11 No. 1 (2026): JEECS (Journal of Electrical Engineering and Computer Sciences) - In press Vol. 11 No. 1 (2026): June Vol. 10 No. 2 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): December Vol. 10 No. 1 (2025): June Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 9 No. 2 (2024): December Vol. 9 No. 2 (2024): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 9 No. 1 (2024): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 9 No. 1 (2024): June Vol. 8 No. 2 (2023): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 8 No. 1 (2023): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 7 No. 2 (2022): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 7 No. 1 (2022): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 6 No. 2 (2021): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 6 No. 1 (2021): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 5 No. 2 (2020): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 5 No. 1 (2020): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 4 No. 2 (2019): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 4 No. 1 (2019): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 3 No. 2 (2018): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 3 No. 1 (2018): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 2 No. 2 (2017): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 2 No. 1 (2017): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 1 No. 2 (2016): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 1 No. 1 (2016): JEECS (Journal of Electrical Engineering and Computer Sciences) More Issue