cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Alfian Maarif
Contact Email
alfianmaarif@ee.uad.ac.id
Phone
-
Journal Mail Official
biste@ee.uad.ac.id
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Buletin Ilmiah Sarjana Teknik Elektro
Published by Universitas Ahmad Dahlan
ISSN : 26857936     EISSN : 26859572     DOI : 10.12928
Core Subject : Engineering,
Electrical & Electronics Engineering
Buletin Ilmiah Sarjana Teknik Elektro (BISTE) adalah jurnal terbuka dan merupakan jurnal nasional yang dikelola oleh Program Studi Teknik Elektro, Fakultas Teknologi Industri, Universitas Ahmad Dahlan. BISTE merupakan Jurnal yang diperuntukkan untuk mahasiswa sarjana Teknik Elektro. Ruang lingkup yang diterima adalah bidang teknik elektro dengan konsentrasi Otomasi Industri meliputi Internet of Things (IoT), PLC, Scada, DCS, Sistem Kendali, Robotika, Kecerdasan Buatan, Pengolahan Sinyal, Pengolahan Citra, Mikrokontroller, Sistem Embedded, Sistem Tenaga Listrik, dan Power Elektronik. Jurnal ini bertujuan untuk menerbitkan penelitian mahasiswa dan berkontribusi dalam pengembangan ilmu pengetahuan dan teknologi.
Arjuna Subject : -
Articles 22 Documents
 1   2   3 
Search results for , issue "Vol. 7 No. 4 (2025): December" : 22 Documents clear
Hybrid Stacking of Multilayer Perceptron, Convolutional Neural Network, and Light Gradient Boosting Machine for Short-Term Load Forecasting Nguyen, Trung Dung; Tuan, Nguyen Anh
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14410

Abstract

Short-term load forecasting (STLF) is essential for scheduling, dispatch, and demand-side management. Real-world load series exhibit rapid local fluctuations and calendar or exogenous influences that challenge single-model approaches. This study proposes a hybrid stacking framework combining a Multilayer Perceptron (MLP), a 1-D Convolutional Neural Network (CNN), and a Light Gradient Boosting Machine (LightGBM), integrated through a ridge-regression meta-learner. The CNN extracts local temporal patterns from sliding windows of the load series, and the MLP processes tabular features such as lags, rolling statistics, and calendar/holiday indicators. At the same time, LightGBM captures nonlinear interactions in the same feature space. Base learners are trained using a rolling TimeSeriesSplit to avoid temporal leakage, and their out-of-fold predictions are used as inputs for the meta-learner. Early stopping regularizes the neural models. Experimental backtests on Queensland electricity demand data (89,136 half-hourly samples) demonstrate that the stacked model achieves markedly lower forecasting errors, with MAPE ≈ 0.81%, corresponding to a 24% reduction compared to CNN (MAPE ≈ 1.07%) and a 32% reduction compared to MLP (MAPE ≈ 1.19%). Regarding runtime, LightGBM is the fastest (25s) but least accurate, while the stacked model requires longer computation (2488s) yet delivers the most reliable forecasts. Overall, the proposed framework balances accuracy and robustness, and it is modular, reproducible, and extensible to additional exogenous inputs or base learners.
Comparison of Machine Learning Algorithms with Feature Engineering for Epileptic Seizure Prediction Based on Electroencephalogram (EEG) Signals Ibrahim, Sutrisno; Rahutomo, Faisal; Henda, Reihan; Aljalal, Majid
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.13145

Abstract

Epilepsy is a neurological disorder marked by recurrent seizures, which can greatly reduce patients' quality of life. Early and accurate seizure prediction is essential for effective clinical intervention and patient safety. This study proposes and evaluates a seizure prediction system using EEG signals processed through machine learning techniques combined with optimized feature extraction methods. The research contribution is the comprehensive comparative analysis of classifier-feature pairs for identifying the most effective configuration for seizure prediction tasks. Three classifiers—Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost)—were systematically compared, each combined with precisely engineered feature extraction methods, including Common Spatial Pattern (CSP), Discrete Wavelet Transform (DWT), statistical features, and frequency domain features. EEG data from seven patients, totaling approximately 68 hours with 40 seizure events, were obtained from the Children's Hospital Boston database. The results demonstrate that XGBoost with CSP features achieved the highest overall accuracy at 88% and specificity at 88%, while XGBoost with DWT features reached the highest sensitivity at 87%. Additional metrics including F1-score (0.85) and AUC-ROC (0.91) confirmed XGBoost's superior performance. Comparison with five recent studies showed our approach offers a 3-5% improvement in accuracy and sensitivity. These findings highlight the critical impact of both classifier selection and feature engineering in improving EEG-based seizure prediction, with implications for developing real-time monitoring systems despite challenges in clinical implementation due to inter-patient variability.
Bi-LSTM and Attention-based Approach for Lip-To-Speech Synthesis in Low-Resource Languages: A Case Study on Bahasa Indonesia Setyaningsih, Eka Rahayu; Handayani, Anik Nur; Irianto, Wahyu Sakti Gunawan; Kristian, Yosi
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14310

Abstract

Lip-to-speech synthesis enables the transformation of visual information, particularly lip movements, into intelligible speech. This technology has gained increasing attention due to its potential in assistive communication for individuals with speech impairments, audio restoration in cases of missing or corrupted speech signals, and enhancement of communication quality in noisy or bandwidth-limited environments. However, research on low-resource languages, such as Bahasa Indonesia, remains limited, primarily due to the absence of suitable corpora and the unique phonetic structures of the language. To address this challenge, this study employs the LUMINA dataset, a purpose-built Indonesian audio-visual corpus comprising 14 speakers with diverse syllabic coverage. The main contribution of this work is the design and evaluation of an Attention-Augmented Bi-LSTM Multimodal Autoencoder, implemented as a two-stage parallel pipeline: (1) an audio autoencoder trained to learn compact latent representations from Mel-spectrograms, and (2) a visual encoder based on EfficientNetV2-S integrated with Bi-LSTM and multi-head attention to predict these latent features from silent video sequences. The experimental evaluation yields promising yet constrained results. Objective metrics yielded maximum scores of PESQ 1.465, STOI 0.7445, and ESTOI 0.5099, which are considerably lower than those of state-of-the-art English systems (PESQ > 2.5, STOI > 0.85), indicating that intelligibility remains a challenge. However, subjective evaluation using Mean Opinion Score (MOS) demonstrates consistent improvements: while baseline LSTM models achieve only 1.7–2.5, the Bi-LSTM with 8-head attention attains 3.3–4.0, with the highest ratings observed in female multi-speaker scenarios. These findings confirm that Bi-LSTM with attention improves over conventional baselines and generalizes better in multi-speaker contexts. The study establishes a first baseline for lip-to-speech synthesis in Bahasa Indonesia and underscores the importance of larger datasets and advanced modeling strategies to further enhance intelligibility and robustness in low-resource language settings.
Optimal PID Controller Based on Different Modified Grasshopper Optimization Algorithm for Nonlinear Single-Input Single-Output System Flaih, Aliaa A.; Karam, Ekhlas H.; Mohammed, Yousra A.
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14394

Abstract

This paper presents a comparative study of the Grasshopper Optimization Algorithm (GOA) with three suggested modified versions—Levy Flight GOA (LFGOA), Dynamic Attraction-Repulsion GOA (DARGOA), and Chaotic GOA (CHGOA)—for tuning Proportional-Integral-Derivative (PID) controller parameters in a nonlinear Single-Input Single-Output (SISO) system. The research contribution is the development and evaluation of CHGOA, which aims to improve convergence speed and transient response stability. The methodology employs exploratory and exploitative mechanisms of each algorithm to optimize PID parameters based on six objective functions. Performance metrics include rise time, settling time, overshoot, peak value, and best fitness obtained from MATLAB/Simulink simulations. A second-order Mass-Spring-Damper (MSD) system is used as a representative nonlinear SISO system. Simulation results indicate that the proposed CHGOA consistently achieves lower fitness values, faster convergence, and stable transient responses compared to LFGOA, DARGOA, and standard GOA, under the tested objective functions. While LFGOA and DARGOA show competitive performance in traditional error metrics, standard GOA exhibits slower convergence in simulation scenarios. In this paper, the performance of the MSD system controlled by the proposed optimal PID with GOAs was also compared with the performance of this system with Nonlinear PIDs (NPIDs) which proposed by previous studies. The comparison results showed the efficiency of our proposed controllers in improving the performance of the MSD system, especially the CHGOA. Overall, the proposed CHGOA provides an effective balance between error minimization, convergence speed, and transient response performance, making it suitable for high-precision real-time applications.
A Hybrid PI–SOSM Control Strategy with Disturbance Observer for Enhanced Dynamic Response of IM Drives Pham, Thanh Tinh; Pham, Ngoc Thuy
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14458

Abstract

This paper proposes a novel hybrid field-oriented control (FOC) strategy for high-performance induction motor (IM) drives, integrating a conventional Proportional–Integral (PI) controller in the speed loop and a Super-Twisting Second-Order Sliding Mode (SOSM) controller in the current loop. The main novelty lies in combining a sliding mode disturbance observer (OB) with a hybrid PI–SOSM structure, enabling real-time estimation and compensation of unknown load torque. The estimated torque is transformed into an equivalent disturbance current, which is directly added to the torque-producing current reference, thereby achieving feedforward disturbance rejection. The novel hybrid structure achives the improved dynamic response and robustness through self-compensated torque disturbance using OB, reduced chattering in current regulation via SOSM, and maintaining PI simplicity in the outer speed loop. Extensive simulation results by MATLAB/Simulink sotfware demonstrates that the hybrid controller offers superior dynamic performance, enhanced robustness against parameter uncertainties and load disturbances, and significantly reduced chattering effects compared with conventional PI–PI FOC.
Smart Cold Storage Based on Photovoltaic with Adaptive Fuzzy Control Approach for Guard Quality of Fish Catch on Fishing Vessels Findiastuti, Weny; Umam, Faikul; Sulaiman, Yoga Aulia; Thinakaran, Rajermani; Dafid, Ach.; Andriansyah, Adi; Yusuf, Ahcmad
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14508

Abstract

This research is motivated by the importance of maintaining the quality of fish catches on fishing vessels, which generally experience a decline in quality due to suboptimal conventional fish storage systems and limited energy supplies at sea. To address these challenges, the development of renewable energy-based cold storage technology through a Solar Power Plant (PLTS) or Photovoltaic system is needed. This research aims to design a PLTS-based smart cold storage system capable of optimally maintaining temperature stability using the Adaptive Fuzzy Control method. It is hoped that fish quality can be maintained and the economic value of fishermen's catches can be increased. This research uses an experimental approach through the design, implementation, and testing of a fuzzy logic-based adaptive control system in real-time. The performance results are then evaluated in maintaining the temperature stability of the cooling room and the efficiency of electrical energy sourced from solar panels. It is hoped that this research can provide real solutions for fishermen, support the economic independence of the fisheries sector, and support the achievement of sustainable development targets (SDGs) 7, 9 12, and 14. During the 24-hour test, the Adaptive Fuzzy Control system in a solar-based refrigerator demonstrated consistent performance in maintaining temperature stability (standard deviation σ = 3.28 °C–3.45 °C). The average refrigerator temperature was recorded at -5.44 °C with a range of -0.9 °C to -12 °C, which remains acceptable for marine fish preservation under superchilling and mild freezing conditions. The battery capacity was at an average of 89.95%, decreasing when there was no power supply and then increasing again during charging, thus reflecting adaptive energy management. The average charging speed was 3.14 A, with a peak of up to 15.6 A at 7–8 hours, then decreasing gradually as the battery was full to prevent overcharging. These findings confirm that the proposed system effectively balances cooling performance and renewable energy utilization. The use of solar photovoltaic energy directly supports SDG 7 (Affordable and Clean Energy), while system innovation and energy optimization align with SDG 9 (Industry, Innovation, and Infrastructure). The prototype demonstrates stable and efficient operation, and the design concept is scalable for practical implementation on small to medium-sized fishing vessels. A preliminary cost analysis indicates up to 50% lower operating costs compared to conventional diesel refrigeration systems.
Exploring Teachers' Perspectives on Culturally Responsive Teaching in Stoichiometry Learning Oriented to Green Chemistry Fitri, Hajidah Salsabila Allissa; Wiyarsi, Antuni; Widarti, Hayuni Retno; Yamtinah, Sri; Pratiwi, Yunilia Nur
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14520

Abstract

This study explores high school chemistry teachers’ perceptions of culturally responsive teaching (CRT) in stoichiometry learning with an orientation toward green chemistry principles. CRT provides a framework for integrating local culture, while green chemistry oriented highlights sustainability in learning abstract topics such as stoichiometry. This qualitative descriptive study involved nine Indonesian chemistry teachers selected purposively from active high school chemistry teachers familiar with stoichiometry and green chemistry. Although the sample size was limited, it provided data saturation and in-depth insights from teachers’ experiences. Data were collected through an open-ended questionnaire covering seven aspects, including teachers’ understanding of CRT, integration of local culture and green chemistry orientation in stoichiometry teaching, and perceived needs. Thematic analysis identified six themes related to teaching barriers, instructional practices, teachers’ CRT understanding, cultural integration, green chemistry orientation, and professional development needs. While teachers expressed strong support for CRT with a green chemistry orientation, implementation remains limited by structural and pedagogical constraints. The study underscores the importance of targeted support to empower teachers in fostering culturally responsive and sustainability-oriented chemistry learning, while acknowledging limitations related to the Indonesian context and the potential for social desirability bias in self-reported data.
Geographic-Origin Music Classification from Numerical Audio Features: Integrating Unsupervised Clustering with Supervised Models Pranolo, Andri; Sularso, Sularso; Anwar, Nuril; Putra, Agung Bella Utama; Wibawa, Aji Prasetya; Saifullah, Shoffan; Dreżewski, Rafał; Nuryana, Zalik; Andi, Tri
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.13400

Abstract

Classifying the geographic origin of music is a relevant task in music information retrieval, yet most studies have focused on genre or style recognition rather than regional origin. This study evaluates Support Vector Machine (SVM) and Convolutional Neural Network (CNN) models on the UCI Geographical Origin of Music dataset (1,059 tracks from 33 non-Western regions) using numerical audio features. To incorporate latent structure, we first applied K-means clustering with the optimal number of clusters (k=2) determined by the Elbow and Silhouette methods. The cluster assignments were used as auxiliary signals for training, while evaluation relied on the true region labels. Classification performance was assessed with Accuracy, Precision, Recall, and F1-score. Results show that SVM achieved 99.53% accuracy (95% CI: 97.38–99.92%), while CNN reached 98.58% accuracy (95% CI: 95.92–99.52%); Precision, Recall, and F1 mirrored these values. The differences confirm SVM’s superior performance on this dataset, though the near-perfect scores also suggest strong separability in the feature space and potential risks of overfitting. Learning-curve analysis indicated stable training, and cluster supervision provided small but consistent benefits. Overall, SVM remains a reliable baseline for tabular music features, while CNNs may require spectro-temporal representations to leverage their full potential. Future work should validate these findings across multiple datasets, apply cross-validation with statistical significance testing, and explore hybrid deep models for broader generalization.
Effective Analysis of Machine Learning Algorithms for Breast Cancer Prediction M, Vanitha; Anitha, V; Jackson, Beulah; F, Anne Jenefer
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.13663

Abstract

Early prognosis of Breast Cancer (BC) is significantly important to cure the disease easily so it is essential to develop methods that is able to aid doctors to get precise prognosis. Hence, a BC prognosis methodology is proposed utilizing Machine Learning (ML) approaches. The target of this paper is to utilize classification techniques to classify tumor types, or benign and malignant cells, using 569 samples from Wisconsin Diagnostic Breast Cancer (WDBC) database. Initially, preprocessing is employed to enhance the data’s quality, which includes data cleaning and min-max normalization. It improves the input breast cancer data's quality, accuracy, and suitability for further analysis. Followed by preprocessing, the ML approaches such as K-Nearest Neighbour (KNN), Random Forest (RF) and Support Vector Machine (SVM) methods are analyzed for the classification of BC data. Each algorithm offers a distinct approach to classification by capturing local patterns in data and handles high-dimensional spaces along with nonlinear boundaries through kernel tricks. The developed work is implemented in python software and comparative analysis is done with traditional methods. The outcomes demonstrates that the proposed KNN classifier shows better performance interms of precision, recall, F1-score with an accuracy of 96.49%, ensuring the earliest diagnosis of breast cancer compared with SVM and RF. This comparative approach enhances the reliability of the proposed methodology and supports the selection of the best-performing algorithm offering valuable insights for real-world clinical decision support systems.
Adaptive FLC-based Shunt Active Power Filter with a PV-Fed DC Link for Improved Current Compensation and THD Mitigation Budi, SH Suresh Kumar; Kiranmayi, R.
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.13804

Abstract

Power quality improvement with traditional controllers (PI, PID, fixed-parameter FLC) is difficult when dealing with nonlinear, time-varying loads and dynamic grid conditions. For microgrids that incorporate renewable energy sources, it is challenging to acquire the precise mathematical models that are necessary for this work. To address power quality challenges, such as distortion of current and Total Harmonic Distortion (THD), produced by nonlinear loads in PV fed systems, such as solar energy conversion, this publication proposes an Adaptive Fuzzy Logic Controller (FLC) based shunt Active Power Filter (APF). An analysis of the power quality enhancement achieved in a distribution power system using a single-stage solar PV integrated shunt APF is presented in this paper. In order to improve load side parameters, such as the elimination of even and odd current harmonics utilizing shunt APF is employed. This filter makes use of a shared DC-link voltage source. In addition, it transfers energy from the PV system's solar panels to the DC link voltage, which is an extra effort. In this paper, It looks at a single-phase inverter that uses an Adaptive FLC to improve parameters on the source and load sides, as well as harmonics, in grid-connected Distributed Generation systems. Also included is a detailed description of the active power filter's chosen current reference generator. Results that have been validated are attained using MATLAB/SIMULINK(R2023b).

Page 1 of 3 | Total Record : 22

 1   2   3 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 8 No. 1 (2026): February Vol. 7 No. 4 (2025): December Vol. 7 No. 3 (2025): September Vol. 7 No. 2 (2025): June Vol. 7 No. 1 (2025): March Vol. 6 No. 4 (2024): December Vol. 6 No. 3 (2024): September Vol. 6 No. 2 (2024): June Vol. 6 No. 1 (2024): March Vol. 5 No. 4 (2023): December Vol. 5 No. 3 (2023): September Vol. 5 No. 2 (2023): June Vol. 5 No. 1 (2023): March Vol. 4 No. 3 (2022): December Vol. 4 No. 2 (2022): Agustus Vol. 4 No. 1 (2022): April Vol. 3 No. 3 (2021): Desember Vol 3, No 2 (2021): Agustus Vol. 3 No. 2 (2021): Agustus Vol 3, No 1 (2021): April Vol. 3 No. 1 (2021): April Vol. 2 No. 3 (2020): Desember Vol 2, No 3 (2020): Desember Vol 2, No 2 (2020): Agustus Vol. 2 No. 2 (2020): Agustus Vol. 2 No. 1 (2020): April Vol 2, No 1 (2020): April Vol 1, No 3 (2019): Desember Vol. 1 No. 3 (2019): Desember Vol 1, No 2 (2019): Agustus Vol. 1 No. 2 (2019): Agustus Vol 1, No 1 (2019): April Vol. 1 No. 1 (2019): April More Issue