cover
Contact Name
-
Contact Email
jte@mail.unnes.ac.id
Phone
-
Journal Mail Official
jte@mail.unnes.ac.id
Editorial Address
Sekaran, Kec. Gn. Pati, Kota Semarang, Jawa Tengah 50229
Location
Kota semarang,
Jawa tengah
INDONESIA
Jurnal Teknik Elektro
ISSN : -     EISSN : 25491571     DOI : https://doi.org/10.15294/jte
Core Subject : Engineering,
Jurnal Teknik Elektro merupakan jurnal yang berisikan tentang artikel dalam bidang Teknik Elektro (Ketenagaan, Elektronika dan Kendali, Pengolahan Isyarat serta Komputer dan Informatika)
Articles 5 Documents
Search results for , issue "Vol. 17 No. 2 (2025)" : 5 Documents clear
Cat Skin Disease Diagnosis Using EfficientNetV2 for Lightweight Processing on Low-Resource Devices Aminah, Fadila Rizka Nur; Mutasodirin, Mirza Alim; Hidayattullah, Muhammad Fikri
Jurnal Teknik Elektro Vol. 17 No. 2 (2025)
Publisher : LPPM Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jte.v17i2.29764

Abstract

Skin diseases are among the most common health issues in domestic cats. However, access to veterinarians is often limited, especially in low-resource settings. Automated image-based detection offers a fast and affordable alternative for early intervention. This paper presents a lightweight approach for diagnosing feline skin diseases using EfficientNetV2 optimized for low-resource devices. A balanced custom dataset consisting of 720 images across nine classes, namely Healthy, Mild/Severe Ringworm, Mild/Severe Acne, Mild/Severe Flea, and Mild/Severe Scabies, was compiled from Kaggle, Roboflow, and Google Images, ensuring ethical use of publicly available data. The images were augmented through rotations (0°, 90°, 180°, 270°) and horizontal flips, resulting in 5,760 images, to enhance model generalization. Five CNN architectures were benchmarked: DenseNet121, MobileNetV2, MobileNetV3, EfficientNetB0, and EfficientNetV2B0. Training was conducted with grid searches over batch sizes {64, 32, 16, 8} and learning rates {1e-3, 5e-4, 2e-4, 1e-4, 5e-5} for up to 300 epochs, and with the Adam optimizer and Reduce-LR-on-Plateau (decay factor 0.5). Early stopping (patience = 10) was used to mitigate overfitting. The best model was selected based on highest validation accuracy. The experiments were conducted on an Intel Xeon 6 CPU (2.2 GHz, 2 vCPUs) in Google Colab without GPU to simulate low-resource deployment. EfficientNetV2B0 achieved the best performance with 99.62% validation accuracy and 99.79% test accuracy, with an average inference latency of 78 ms/frame. Compared to previous studies focusing on heavyweight models or conventional ML using handcrafted features, this work highlights the feasibility of deploying an accurate real-time diagnostic pipeline on edge devices.
Externally Validated Deep Learning Model for Multi-Disease Classification of Chest X-Rays Kusumawati, Weny Indah; Permana, Zendi Zakaria Raga; Puspasari, Ira
Jurnal Teknik Elektro Vol. 17 No. 2 (2025)
Publisher : LPPM Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jte.v17i2.29892

Abstract

Accurate classification of chest X-ray (CXR) images is vital for early detection of thoracic diseases such as COVID-19, Tuberculosis, and Pneumonia, particularly in regions with limited radiological expertise. While deep learning has shown promise in CXR interpretation, many existing models rely solely on internal datasets, risking overfitting and poor generalizability. Furthermore, inadequate tuning of network architectures may limit robustness across varied imaging conditions. This study presents an externally validated deep learning framework based on Convolutional Neural Networks (CNNs) for multi-disease CXR classification. This study compared a baseline CNN with two convolutional layers against a tuned architecture with three layers across multiple image resolutions (64×64, 112×112, 224×224). The proposed model employs transfer learning with a pre-trained CNN, fine-tuned for four-class classification using a softmax output layer. Training was performed with the Adam optimizer (learning rate: 0.0001, batch size: 32) and categorical cross-entropy loss, for up to 50 epochs with early stopping. Internal validation showed the tuned model outperformed the baseline, achieving 0.97 accuracy and an F1-score of 0.89. External validation confirmed superior generalizability, with the tuned model attaining an F1-score of 0.83 and an AUC of 0.97 at 112×112 resolution, compared to the baseline’s F1-score of 0.79 and AUC of 0.94. These results highlight the potential of optimized CNN architectures as reliable, scalable tools for radiological decision support in resource-limited healthcare systems. Future work will incorporate explainable AI methods and real-world clinical validation to ensure safe, interpretable deployment.
Portable EMG System for IoT Using MQTT Yuniati, Anis; Ramadhani, Bintang; Rakhmadi, Frida Agung; Sumarti, Heni
Jurnal Teknik Elektro Vol. 17 No. 2 (2025)
Publisher : LPPM Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jte.v17i2.33839

Abstract

Conventional electromyography (EMG) systems in clinical settings present limitations including high examination costs (500,000-1,500,000 IDR), bulky equipment, and lack of remote monitoring capabilities. This study develops and validates a portable Internet of Things (IoT)-based EMG system utilizing Message Queuing Telemetry Transport (MQTT) protocol for wireless muscle activity monitoring. The system integrates an EMG V3 sensor module with NodeMCU ESP8266 microcontroller, powered by dual 18650 batteries. Implementation utilized Arduino IDE and IoT MQTT Panel application. Validation comprised functional suitability testing (ISO/IEC 25010:2012), signal characteristics analysis across five subjects with 10 trials each, and repeatability precision evaluation (ISO 17025:2017). The system demonstrated 100% functional suitability. EMG signal characteristics showed average peak-to-peak voltage of 8.95±0.62 mV during relaxation and 10.48±0.58 mV during contraction, with Root Mean Square (RMS) voltage of 1.38±0.11 mV and 1.94±0.21 mV, respectively. Signal frequency-maintained consistency at approximately 50 Hz. Overall repeatability precision achieved 97.62%. This portable EMG system addresses conventional system limitations through wireless connectivity and reduced cost while maintaining measurement accuracy suitable for muscle health monitoring applications.
Performance Evaluation of NARX-CG Model for Electricity Forecasting: Bali Blackout Case Study Alaqsa, Tengku Reza Suka; Aini, Zulfatri
Jurnal Teknik Elektro Vol. 17 No. 2 (2025)
Publisher : LPPM Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jte.v17i2.35519

Abstract

Bali experienced a widespread blackout in May 2025 that disrupted economic and social activities across the island, revealing weaknesses in electricity demand forecasting and system resilience. This study evaluates the performance of a Hybrid Nonlinear Autoregressive with Exogenous Inputs-Conjugate Gradient (NARX-CG) model as an advanced electricity forecast. The dataset covers the 2018-2023 period and includes six variables: electricity energy, connected capacity, number of customers, tariffs, Gross Regional Domestic Product (GRDP), and population, aligned with the national electricity planning framework. The NARX-CG model was developed using a 6-12-6-1 network architecture and trained with tansig transfer function. Forecasting performance was evaluated using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) metrics. Results show that the NARX-CG model achieved an MSE of 0.09853 and an average MAPE of 8.12%, outperforming conventional projections with a MAPE of 28.48%. Yearly evaluations show consistent model stability, with the lowest MAPE values of 1.93% and 5.86% in 2023 and 2022, respectively. The NARX-CG model effectively captures nonlinear temporal dependencies, enhances predictive accuracy, and contributes to improved power system reliability and resilience, providing valuable insights for adaptive energy planning following the 2025 Bali blackout.
Wideband Multi-Resonant Microstrip Patch Antenna for Wireless Communication Systems Ulfah, Mia Maria; Asthan, Rheyuniarto Sahlendar
Jurnal Teknik Elektro Vol. 17 No. 2 (2025)
Publisher : LPPM Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jte.v17i2.35545

Abstract

The increasing demand for high-performance wireless communication systems has driven the development of compact antennas that can support wideband operation, particularly in the 5 GHz frequency range. Microstrip patch antennas (MPAs) remain attractive for such applications due to their low profile and ease of integration, although achieving a wide impedance bandwidth remains a key challenge. This paper presents a low-profile MPA with a wideband response designed for the 5 GHz band of wireless communication systems. The proposed MPA is implemented on a single-layer FR-4 substrate with a thickness of 1.6 mm and is excited using a coaxial probe feed. To achieve a wide impedance bandwidth, a U-shaped patch is utilized as the primary radiator, complemented by a slot, a parasitic element, and a rectangular ring surrounding the main resonator, aiming to generate multiple resonant modes and improve impedance matching. The influence of each modification on antenna performance is systematically analyzed. To validate its performance, the proposed MPA is fabricated and measured, with the obtained results compared to the simulated ones. Simulation and measurement results show good agreement, confirming that the proposed MPA achieves a wideband response with a fractional bandwidth of 18.8% and a peak realized gain of 4.85 dBi. These results highlight the effectiveness of the proposed design and demonstrate its potential for compact and wideband wireless communication devices operating around 5 GHz frequency range.

Page 1 of 1 | Total Record : 5