cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Andi Adriansyah
Contact Email
andi@mercubuana.ac.id
Phone
+628111884220
Journal Mail Official
sinergi@mercubuana.ac.id
Editorial Address
Fakultas Teknik Universitas Mercu Buana Jl. Raya Meruya Selatan, Kembangan, Jakarta 11650 Tlp./Fax: +62215871335
Location
Kota adm. jakarta barat,
Dki jakarta
INDONESIA
Sinergi
Published by Universitas Mercu Buana
ISSN : 14102331     EISSN : 24601217     DOI : https://dx.doi.org/10.22441/sinergi
Core Subject : Engineering,
Civil Engineering, Building, Construction & Architecture Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering
SINERGI is a peer-reviewed international journal published three times a year in February, June, and October. The journal is published by Faculty of Engineering, Universitas Mercu Buana. Each publication contains articles comprising high quality theoretical and empirical original research papers, review papers, and literature reviews that are closely related to the fields of Engineering (Mechanical, Electrical, Industrial, Civil, and Architecture). The theme of the paper is focused on new industrial applications and energy development that synergize with global, green and sustainable technologies. The journal registered in the CrossRef system with Digital Object Identifier (DOI). The journal has been indexed by Google Scholar, DOAJ, BASE, and EBSCO.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 534 Documents
 50   51   52   53   54 
An effective and efficient vehicle detection using ER-EMA-YOLOv10n Kutika, Imanuel; Lahimade, Vicky Nolant Setyanto; Todingan, Tomi Heri Julius; Prasetya, Hebron; Sentinuwo, Steven Ray; Putro, Muhamad Dwisnanto
SINERGI Vol 30, No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2026.1.017

Abstract

Vehicle detection plays a key role in automating traffic analysis, a field that continues to advance rapidly. Vision-based systems identify vehicle types and sizes, but achieving high accuracy and efficiency remains a challenge. Reliable real-world deployment requires optimized models that balance performance and computational cost. YOLOv10n, the most efficient version of the YOLO family, offers a solid foundation for lightweight feature extraction. To improve its detection performance, this study proposes an enhanced version of YOLOv10n by incorporating a scale-aware attention mechanism. We proposed the Expanded Refinement Efficient Multi-Scale Attention (ER-EMA) module, which enhances feature encoding by capturing vehicle characteristics across multiple receptive fields. ER-EMA consists of two core components: the Expanded Converted Inverted Block (ECIB) and the Convolutional Refinement Block (CRB). These components use diverse convolutional kernels to extract and refine multi-frequency spatial features. Integrating ER-EMA into the YOLOv10n framework produces a more compact and accurate detection model. Experimental results show that the proposed model increases mAP@50 by 1%, while reducing the number of parameters by 0.1M and computation by 0.1 GFLOPS on the Vehicle-COCO dataset. On the UA-DETRAC benchmark, it achieves a 4% improvement in mAP@50:95, with a reduction of 0.2M in parameters and 0.4 GFLOPS in computational efficiency—outperforming the original YOLOv10n and prior methods in both performance and computational efficiency.
Enhanced Classification of Multi Abnormal Brain Tumors Detection Using Customized Inception V3 Arumalla, Nagaraju; Gampala, Veerraju
SINERGI Vol 30, No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2026.1.020

Abstract

A brain tumor (BT) is considered to be one of the most fatal diseases in the world, which also demands a very precise and early detection to be successfully addressed. The irregularities in the brain can be detected with the help of a magnetic resonance image, or MRI. Menigoma, glioma, pituitary tumours, and no-tumor are four categories of BT to be classified in this work according to an enhanced transfer learning (TL) approach, generated by the pretrained Inception V3 model. The preprocessing pipeline is new and includes data augmentation to reduce overfitting, a bilateral filter to remove noise, background cropping, and image scaling. The proposed method achieves training accuracy of 94.9% and validation accuracy of 93.8%. With a change in the hyperparameter (k-value), the validation and training accuracies improve to 95.3% and 96.8%, respectively. Furthermore, the model has a high level of generalization, where sensitivity is 92.8 percent, and specificity is 93.5 percent. The combination of transfer learning with the high-level enhancement and strengthening of pictures is novel. Nevertheless, among the factors that can affect generalizability, the variety and size of datasets are important. This model should be confirmed through further research using larger, more diverse datasets and explored in the context of clinical interpretability.
Comparative analysis of EEG pre-processing in ASD using Hanning and Blackman Harris filters Melinda, Melinda; Waladah, Buleun; Yunidar, Yunidar; Mahfuzha, Raudhatul; Gazali, Syahrul; Rusdiana, Siti; Basir, Nurlida
SINERGI Vol 30, No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2026.1.023

Abstract

This study investigates the effectiveness of two Finite Impulse Response (FIR) filter designs based on the Hanning and Blackman-Harris windows for preprocessing electroencephalography (EEG) signals collected from both neurotypical individuals and those diagnosed with Autism Spectrum Disorder (ASD). EEG signals were recorded using a 16-channel setup and band-pass filtered between 0.5 and 40 Hz to isolate relevant neural activity. Subsequently, the signals were processed independently using each FIR filter type. Performance evaluation was conducted using four quantitative metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Signal-to-Noise Ratio (SNR), and Power Spectral Density (PSD). The Hanning window filter showed MAE values ranging from 0.079 to 0.325, MSE from 0.026 to 0.177, SNR between 7.56 and 15.86 dB, and PSD values from 5.3 to 9.08 × 10⁻³. These results demonstrate good noise attenuation while preserving signal morphology. In contrast, the Blackman-Harris window produced higher MAE (0.061–0.318) and MSE (0.019–0.172) but achieved significantly greater SNR improvements (7.77–17.4 dB) and tighter control over PSD (4.904 – 8.442 × 10⁻³), indicating superior noise suppression and reduced spectral leakage. A paired t-test confirmed that differences in all four performance metrics were statistically significant (p < 0.05) across both neurotypical and ASD subject groups. Despite the Hanning filter's computational simplicity, the Blackman-Harris filter demonstrated more robust performance, making it a more suitable choice for high-fidelity EEG signal analysis in clinical diagnostics and neuroscience research.  
Overestimation of load-resisting capacity in double-span welded steel beams: a comparative FEM study incorporating ductile damage and element deletion Mohd Zaman, Nor Idahyu; Subki, Nur Ezzaryn Asnawi; Hamid, Yazmin Sahol; Mansor, Hazrina
SINERGI Vol 30, No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2026.1.027

Abstract

The study investigates how different finite element modelling assumptions affect the predicted load-resisting behavior of welded beam-column connections in double-span steel beam systems subjected to column-removal scenarios. Existing numerical studies commonly neglect fracture and material degradation, which may result in unconservative estimates of structural capacity. To address this limitation, nonlinear static analyses were performed in ABAQUS using two simplified modelling approaches: (i) non-fracture models that exclude plasticity damage and element deletion, and (ii) fracture-based models that incorporate ductile damage criteria with element deletion. Structural responses were evaluated in terms of load-displacement relationships, moment-rotation behavior, and the development of tensile catenary action. The results indicate that accounting for plasticity damage and fracture significantly alters the predicted response, leading to markedly lower strength and deformation capacity compared to non-fracture models. In particular, the inclusion of fracture mechanisms resulted in an approximate 50% reduction in load-carrying capacity and catenary resistance. These findings demonstrate that neglecting fracture behavior can substantially overestimate the robustness of welded beam-column connections under extreme loading conditions. The study underscores the importance of structural performance in progressive collapse analyses. 

Page 54 of 54 | Total Record : 534

 50   51   52   53   54 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol 30, No 1 (2026) Vol 29, No 3 (2025) Vol 29, No 2 (2025) Vol 29, No 1 (2025) Vol 28, No 3 (2024) Vol 28, No 2 (2024) Vol 28, No 1 (2024) Vol 27, No 3 (2023) Vol 27, No 2 (2023) Vol 27, No 1 (2023) Vol 26, No 3 (2022) Vol 26, No 2 (2022) Vol 26, No 1 (2022) Vol 25, No 3 (2021) Vol 25, No 2 (2021) Vol 25, No 1 (2021) Vol 24, No 3 (2020) Vol 24, No 2 (2020) Vol 24, No 1 (2020) Vol 23, No 3 (2019) Vol 23, No 2 (2019) Vol 23, No 1 (2019) Vol 22, No 3 (2018) Vol 22, No 2 (2018) Vol 22, No 1 (2018) Vol 21, No 3 (2017) Vol 21, No 2 (2017) Vol 21, No 1 (2017) Vol 20, No 3 (2016) Vol 20, No 2 (2016) Vol 20, No 1 (2016) Vol 19, No 3 (2015) Vol 19, No 2 (2015) Vol 19, No 1 (2015) Vol 18, No 3 (2014) Vol 18, No 2 (2014) Vol 18, No 1 (2014) Vol 17, No 3 (2013) More Issue