cover
Contact Name
Machrus Ali
Contact Email
lppm.undar1965@gmail.com
Phone
+6281330002213
Journal Mail Official
jurnal.jeetech@gmail.com
Editorial Address
Jl. Gus Dur No.29A, Mojongapitindah, Mojongapit, Kec. Jombang, Kabupaten Jombang, Jawa Timur 61419
Location
Kab. jombang,
Jawa timur
INDONESIA
Jurnal JEETech
Published by Universitas Darul Ulum
ISSN : 29647320     EISSN : 27225321     DOI : 10.32492/jeetech.v7i1
Core Subject :
Jurnal JEETech: Journal Of Electrical Engineering And Technology. Journal of Darul Ulum University Jombang in collaboration with the Faculty of Engineering, Darul Ulum University Jombang with the Indonesian Electrical Engineering Higher Education Forum (FORTEI). Region VII. East Java. This journal contains research results in the fields of Power Engineering, Telecommunication Engineering, Computer Engineering, Control and Computer Systems, Electronics, Information Technology, Informatics, Data and Software Engineering, Biomedical Engineering. All submitted articles must report original, previously unpublished, experimental or theoretical research results that are not published and are being considered for publication elsewhere.
Arjuna Subject : -
Articles 111 Documents
Implementation YOLOv5 algorithm for Detection Digital Image - Based Banana Diseases Anis Yusrotun Nadhiroh; Moh Jasri; Wali Ja’far Shudiq
Jurnal JEETech Vol. 7 No. 1 (2026): Nomor 1 May
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i1.7113

Abstract

Banana is one of the tropical fruit commodities with high economic value, but it is vulnerable to diseases such as anthracnose (spot), crown rot, and fruit rot, which negatively affect yield and fruit quality. The manual detection method, which is still commonly used, has limitations in terms of accuracy and efficiency. Therefore, this study aims to develop a banana disease detection system based on digital images using the You Only Look Once version 5 (YOLOv5) method. This research applies a quantitative experimental approach with a dataset consisting of 1,005 images that were labeled using the Roboflow platform. The training process was carried out in Google Colaboratory with four epoch configurations, namely 20, 50, 80, and 100. Model performance was evaluated using accuracy, precision, recall, F1-score, and mean Average Precision (mAP), as well as confusion matrix visualization. The best training results at 50 epochs achieved an average mAP-50 of 0.817%. The final results of this study demonstrate that YOLOv5 is effective in automatically and accurately detecting banana diseases. The web-based implementation provides added value in terms of accessibility and ease of use. The study recommends further development with a larger dataset and the utilization of mobile applications to support field implementation in real time.
TAM, Emotional Engagement, and Trust on AR Virtual Try-On Behavioral Intention in Shopee Cahya Ade Ningrum; Muawan Bisri; Fathoni Dwiatmoko
Jurnal JEETech Vol. 7 No. 1 (2026): Nomor 1 May
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i1.7114

Abstract

The rapid development of digital shopping encourages e-commerce platforms  to continue to innovate through the application of immersive technology, one of which is  the Augmented Reality (AR) Virtual Try-On (VTO) feature that facilitates consumers in simulating products virtually before purchasing decisions are made. This study was designed to investigate the contribution of Perceived Ease of Use (PEOU), Perceived Usefulness (PU), Emotional Engagement (EE), and Trust (TR) to the Behavioral Intention (BI) of AR VTO feature users in Shopee, Indonesia. The study adopted a quantitative approach through surveying 500 active Shopee users who had used the feature at least once, with data analysis using the Structural Equation Modeling-Partial Least Squares (SEM-PLS) method assisted by SmartPLS 4. All instruments were declared valid and reliable based on the results of the outer model evaluation. The four variables were simultaneously proven to have a positive and significant influence on BI. The novelty of this research lies in the simultaneous integration of the cognitive dimensions of TAM, affective, and trust in a single analytical framework applied specifically to the context of Shopee's AR VTO in the Indonesian market, an approach that has not been explored much in the literature before. The research findings have practical implications for Shopee developers in designing a more intuitive, emotionally responsive, and data-secure AR interface, to encourage wider adoption of technology among Indonesian digital consumers.
Integrasi WhatsApp Gateway dan Cloud Computing pada Sistem Absensi Digital Terpadu Siswa (SAGITA) Gustiawan Maula Rizki; Fathoni Dwiatmoko; Agus Komarudin
Jurnal JEETech Vol. 7 No. 1 (2026): Nomor 1 May
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i1.7111

Abstract

The integration of Information and Communication Technology (ICT) in vocational high schools demands agile and accurate administrative governance. Manual attendance monitoring often collides with data accuracy issues and recapitulation inefficiency. This study aimed to design, develop, and evaluate the Integrated Student Digital Attendance System (SAGITA) utilizing a cloud computing architecture at SMK NU Kaplongan, accommodating 1,186 students across 38 study groups. The system integrated the Google Workspace ecosystem (Google Forms and Sheets) with Google Apps Script (GAS) and a local WhatsApp Gateway API for real-time information broadcasting. Employing an applied research methodology with a prototyping approach, the evaluation was conducted through functional testing (Black-box) and administrative impact testing (Pre-test/Post-test). The results showed that the system successfully sent notifications with an average latency of 3-5 seconds. The administrative evaluation indicated a measurable efficiency in recapitulation time and a decrease in reporting delays. The system's continuity relies heavily on physical supporting infrastructure, including the availability of a Virtual Private Server (VPS), a Public IP, and an Uninterruptible Power Supply (UPS). This low-code model offers a cost-effective alternative administrative solution for large-scale educational institutions
K-Means Clustering for Primary Education Inequality in Serang City Ari Sopiandi; Muawan Bisri; Eko Aziz Apriadi; Agus Komarudin
Jurnal JEETech Vol. 7 No. 1 (2026): Nomor 1 May
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i1.7115

Abstract

Educational inequality remains a persistent issue in various regions, including Serang City. Differences in access to and quality of education across areas are influenced by several factors such as the number of schools, students, and teaching staff. However, available educational data are generally presented only in the form of descriptive statistics, which are not sufficient to provide in-depth insights into the patterns of inequality. Therefore, a computational-based approach is needed to analyze educational data more effectively. This study aims to analyze trends in educational development and map educational inequality in Serang City using a data mining approach with the K-Means algorithm. The data used in this study consist of educational data obtained from the Serang City Education Office, Dapodik, and BPS, including the number of schools, the number of students, and the number of teaching staff. The analysis process is carried out through data preprocessing, normalization, and data clustering using the K-Means algorithm with the help of RapidMiner software. The results show that educational data can be grouped into several clusters representing the level of educational conditions across regions. Each cluster has different characteristics, which can be used to identify areas with high and low levels of educational inequality. Thus, the data mining approach is able to provide a more systematic overview of educational conditions and support data-driven decision-making
Prototipe AI-IoT Edge Berbasis Raspberry Pi dan TinyML untuk Pemantauan Jaringan Kampus secara Real-Time Bima Aulia Firmandani; F Yudi Limpraptono; Michael Ardhita; Machrus Ali
Jurnal JEETech Vol. 7 No. 1 (2026): Nomor 1 May
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i1.7112

Abstract

Complex campus networks featuring server-based services and the growing Internet of Things (IoT) require near-real-time monitoring systems without incurring significant overhead. This study proposes a lightweight Artificial Intelligence-Internet of Things (AI-IoT)-based network monitoring prototype on an edge computing platform, utilizing an unsupervised autoencoder for anomaly detection. This prototype is implemented out-of-band on a Raspberry Pi 4 Model B device that serves as both a collection and inference node. The deep learning model on the TensorFlow Lite framework is compressed using TinyML for compatibility with small devices. The results use a dataset of 600,000 labeled flows that illustrate the trade-off in operational flexibility. At the P70 threshold, an F1-Score of 0.60 (precision 0.96, recall 0.43) is obtained, and in the P95 scenario, false positives can be completely eliminated. The edge infrastructure demonstrated excellent performance with an average batch processing latency of 74 ms and a throughput of over 300 flows/second with a constant Random Access Memory (RAM) usage of 2.8%.
Evaluation of E-Learning Governance Using COBIT 2019 DSS at Universitas Indonesia Mandiri Sella Andira Bintang Wulandari; Agus Komarudin; Ribut Julianto; Muawan Bisri
Jurnal JEETech Vol. 7 No. 2 (2026): Nomor 2 November (In Progress)
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i2.7201

Abstract

This study aims to evaluate the governance of e-learning services using the COBIT 2019 framework, specifically within the Deliver, Service, and Support (DSS) domain. The research adopts a quantitative evaluative approach with a cross-sectional design, where data were collected from 30 respondents consisting of IT staff, lecturers, and students using a structured questionnaire. Data analysis was conducted through validity and reliability testing, capability level measurement, and gap analysis. The results show that all questionnaire items are valid and reliable, indicating that the instrument is suitable for measuring e-learning governance. The capability level analysis reveals an average score of 3.34, corresponding to Level 3 (Established Process). This indicates that governance processes have been implemented in a structured and consistent manner, although they have not yet reached the optimal level. The gap analysis shows that most DSS subdomains have a gap value of 2 compared to the target Level 5 (Optimizing Process), indicating the need for further improvement. The largest gaps are identified in incident management, problem management, service continuity, and business process control, suggesting that governance practices are still predominantly reactive. Therefore, organizations are encouraged to strengthen proactive governance through continuous improvement, integrated monitoring, and data-driven decision-making. This study provides practical insights for improving e-learning service governance and supports decision-making in higher education institutions. However, the findings are based on respondents’ perceptions and a cross-sectional design, which may not fully capture dynamic changes over time.
Performance Comparison of On-Grid and Off-Grid Hybrid Photovoltaic Systems for the TRET Building Muhammad Ruswandi Djalal; Marhatang Marhatang; Muhammad Sudaryono; Ahmad Zahir
Jurnal JEETech Vol. 7 No. 2 (2026): Nomor 2 November (In Progress)
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i2.7202

Abstract

The Renewable Energy Engineering Technology (TRET) Building has a high demand for electrical energy, requiring an efficient and sustainable energy supply system. One potential solution is the implementation of a Solar Power Plant (PLTS). This study aims to compare the technical performance and economic feasibility of hybrid, on-grid, and off-grid PLTS systems applied to the TRET Building at Politeknik Negeri Ujung Pandang. The research was conducted over five months through literature review, system design, implementation, testing, and data analysis. Performance evaluation was carried out using indicators such as Specific Yield, Reference Yield, Performance Ratio (PR), and system efficiency, while economic feasibility was analyzed through investment cost, operational cost, energy production cost, Net Present Value (NPV), Profitability Index (PI), and Internal Rate of Return (IRR). The results indicate that the hybrid PLTS achieved the best technical performance, with a Performance Ratio of 122.5% and system efficiency of 23.58%, compared to the on-grid system with 106.4% PR and 20.46% efficiency, and the off-grid system with 56.1% PR and 10.73% efficiency. Economically, the hybrid system required the highest investment cost of Rp 21,835,139.00; however, it also produced the highest NPV and IRR values, indicating better long-term feasibility and sustainability. Therefore, the hybrid PLTS system is considered the most optimal solution for application in the TRET Building due to its superior technical performance, operational reliability, and economic sustainability.
Support System Forecasting Recipients of Basic Food Donations From Serambi Dakwah Using The Simple Additive Weighting Method Ahmad Hadinata Ahfan; Muhammad Rizal Husain Muttaqien; Eko Aziz Apriadi; M. Fikri Akbar
Jurnal JEETech Vol. 7 No. 2 (2026): Nomor 2 November (In Progress)
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i2.7203

Abstract

Alms basic food is an activity of distributing groceries/basic needs such as rice, oil, sugar, etc. to the poor, especially those who live around the Serambi Da'wah organisation. The da'wah platform located in Bantul, Yogyakarta has one of its routine activities, namely the basic food items which is carried out every month. The number of donors for this activity continued to increase, and there were more and more of them. Apart from that, the number of recipients of alms was increasing rapidly, so the administrators began to find it difficult to determine who was eligible to receive alms. This study attempts to find a solution to this condition by using one of the methods in the decision-making system (DSS), namely the Simple Additive Weighting (SAW) method. This method is expected to be able to present a ranking of each feasible alternative choice of prospective alms recipients based on the specified criteria. Based on the results of research conducted using the SAW method, it was found that prospective recipients of basic necessities obtained the highest rank by taking into account various existing criteria. The results of data processing from prospective recipients of basic necessities who obtained the highest rank were 0.93. Determining alms recipients using the SPK method makes it easier for the management of the da'wah porch to distribute alms in a more targeted manner.
Implementing YouTube-Assisted Shadowing in Arabic Listening Instruction: A Pesantren Case Study Paisal Paisal; Abdul Qodir
Jurnal JEETech Vol. 7 No. 2 (2026): Nomor 2 November (In Progress)
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i2.7205

Abstract

Learners of Arabic in Indonesian Islamic boarding schools (pesantren) often read classical texts competently but struggle to follow spoken Arabic. This study examined how YouTube-assisted shadowing was implemented in Arabic listening lessons at the Madrasah Bahasa of Pondok Pesantren Wali Songo Cukir, Jombang, how students perceived the lessons, and which factors supported or constrained implementation. A qualitative case study was conducted over approximately three months in the 2025–2026 academic year. Participants were one Arabic teacher, 12 female students, and one academic coordinator, selected purposively. Data from 12 classroom observations, 14 semi-structured interviews, and lesson documents were analysed through data condensation, data display, and conclusion drawing. Implementation followed a six-stage cycle: video selection, pre-listening preparation, gist listening, shadowing practice, comprehension checking, and reflection. Placing meaning-focused activities before and after shadowing kept the practice from becoming mechanical imitation. Students reported greater engagement and described perceived gains in following spoken Arabic, pronunciation, vocabulary, and speaking confidence; these reports were not verified by test scores. Teacher scaffolding, visual context, repeated playback, student motivation, and the Arabic-use environment of the pesantren supported implementation, whereas fast native speech, unfamiliar vocabulary, unstable internet connection, and mixed proficiency levels constrained it. The study provides a documented lesson sequence that Arabic teachers in comparable settings can adapt and test.
Cross-Layer Seismic Data Gap Detection Using Bi-GRU Autoencoder and Hybrid CNN-BiGRU Aziz Setiawan; Ahmad Musyafa; Makhsun; Ceppy Multi Anggara
Jurnal JEETech Vol. 7 No. 2 (2026): Nomor 2 November (In Progress)
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i2.7204

Abstract

Continuous seismic waveform transmission is essential to the Indonesia Tsunami Early Warning System (InaTEWS), yet transmission gaps may originate from either communication-network degradation or disruption in the SeedLink application stream. This study develops an unsupervised cross-layer anomaly-detection framework for the TEBBI seismic site and compares a Bidirectional Gated Recurrent Unit (BiGRU) autoencoder with a Hybrid CNN-BiGRU model. Integrated Layer-3 PRTG and Layer-7 SeedLink logs from October 2025 to March 2026 produced 262,080 one-minute records with six operational features. Domain-aware missing-value treatment, fixed-range normalization, 30-minute sliding windows, chronological 80:10:10 partitioning, and one-class training on normal windows were applied. Validation reconstruction errors were converted into model-specific F1-max thresholds. The hybrid model achieved MAE 0.016637, RMSE 0.051577, F1-score 0.8737, and AUC-ROC 0.9595, compared with 0.016806, 0.051810, 0.8728, and 0.9590 for BiGRU. Cross-layer diagnosis separated normal operation, Layer-3 failure, Layer-7 blind spots, and systemic disruption; Layer-7 or systemic states represented 10.27% and 10.08% of test windows for the hybrid and BiGRU models, respectively. Inter-model diagnostic agreement reached 97.70%. The principal contribution is source-oriented, site-specific diagnosis that supports more targeted seismic-transmission troubleshooting at TEBBI

Page 11 of 12 | Total Record : 111