Jurnal JEETech

Cross-Layer Seismic Data Gap Detection Using Bi-GRU Autoencoder and Hybrid CNN-BiGRU

Aziz Setiawan — 2026-11-03

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

Support System Forecasting Recipients of Basic Food Donations From Serambi Dakwah Using The Simple Additive Weighting Method

Ahmad Hadinata Ahfan — 2026-11-03

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.

Analysis of the Effect of Environmental Parameters on Photovoltaic Output Performance Using Multivariate Regression

Urmilah — 2026-11-04

The utilization of solar energy through photovoltaic (PV) technology has continued to expand as a sustainable solution for electricity generation. However, photovoltaic performance is influenced by environmental factors, including humidity, ambient temperature, solar irradiance, and wind speed. This study aims to analyze the effects of these factors on the current, voltage, and power output of monocrystalline and polycrystalline photovoltaic panels using the Multivariate Regression method. Before model development, classical assumption tests, including normality, linearity, multicollinearity, heteroscedasticity, and autocorrelation, were conducted. Partial effects were evaluated using the t-test, while simultaneous effects were assessed using Pillai's Trace statistic. The results indicate that, for the monocrystalline panel, solar irradiance significantly affects current, voltage, and power output. For the polycrystalline panel, solar irradiance significantly affects current and power, humidity affects current and power, and wind speed affects current and voltage. Ambient temperature has no significant partial effect on either panel type. Simultaneous analysis identifies solar irradiance as the most dominant factor influencing the performance of both photovoltaic panels.

Implementing YouTube-Assisted Shadowing in Arabic Listening Instruction: A Pesantren Case Study

Paisal Paisal — 2026-11-03

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.

Performance Comparison of On-Grid and Off-Grid Hybrid Photovoltaic Systems for the TRET Building

Muhammad Ruswandi Djalal — 2026-10-22

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.

Evaluation of E-Learning Governance Using COBIT 2019 DSS at Universitas Indonesia Mandiri

Sella Andira Bintang Wulandari — 2026-06-21

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.