cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Indonesian Journal of Electrical Engineering and Computer Science
Published by Institute of Advanced Engineering and Science
ISSN : 25024752     EISSN : 25024760     DOI : -
Core Subject :
Arjuna Subject : -
Articles 9,226 Documents
 919   920   921   922   923 
Enhanced long-term recurrent convolutional network for video classification Manal Benzyane; Mourade Azrour; Said Agoujil
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp174-182

Abstract

Video classification is essential in computer vision, enabling automated understanding of dynamic content in applications such as surveillance, autonomous systems, and content recommendation. Traditional long-term recurrent convolutional network (LRCN) models, however, often struggle to capture complex spatio-temporal patterns, limiting classification performance across diverse video datasets. To address this limitation, we propose an enhanced LRCN with architectural refinements, optimized filter sizes, and hyperparameter tuning, improving both temporal modeling and spatial feature extraction. Experimental results on three benchmark datasets DynTex, UCF11, and UCF50 demonstrate that the proposed model achieves accuracies of 0.90 on DynTex (+26.8% over standard LRCN), 0.92 on UCF11 (+19.5%), and 0.94 on UCF50 (+1.1%), consistently outperforming ConvLSTM, LRCN, and other state-of-the-art approaches. These findings indicate that the enhanced LRCN effectively captures spatial and temporal dynamics in video sequences, setting a new benchmark for video classification. The study highlights the impact of architectural innovation and parameter optimization, providing a solid foundation for future research on scalable and efficient deep learning models for dynamic content analysis.
ViHateT5 with LoRA: efficient vietnamese toxic news classification on social media Tran Duc Duong; Hai Hoan Do
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp123-130

Abstract

We propose an efficient transformer-based approach to detect toxic or misleading news in Vietnamese social media. Motivated by the societal harm of viral misinformation in Vietnam, we fine-tune a Vietnamese T5 model (ViHateT5) on a new dataset of 2,962 social-media news snippets labeled as toxic vs. non-toxic. We use low-rank adaptation (LoRA) to inject trainable layers into ViHateT5, allowing high accuracy with minimal additional parameters. Our model achieves 97.5% macro-F1 on a held-out test set, significantly higher than a PhoBERT baseline by 2.7 points. By focusing on Vietnamese data and a parameter-efficient method, we demonstrate a practical pipeline for low-resource fake-news detection. These results suggest that transformer pretraining on social-media text can effectively capture the subtle cues of deceptive or defamatory news. Limitations: the current model is trained on a specific labeled dataset and may not generalize to all domains; future work should evaluate its fairness and biases in deployment.
Correlation-based assessment of 4G LTE network performance during rainfall events in tropical regions Ngozi C. Eli-Chukwu; Uma Uzubi Uma; Handel Emezue; Ogechi Akudo Nwogu; Ogah E. Oga; Calister N. Ogbonna-Mba; Samuel I. Ezichi
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp105-114

Abstract

This paper presents a performance evaluation of a fourth-generation (4G) cel lular network under adverse weather conditions in a tropical region. While the impact of rainfall on frequencies above 10 GHz is well documented, this study addresses the research gap concerning 4G LTE performance (sub-6 GHz) in high-precipitation environments such as Nigeria. Using a drive-test approach with TEMS Investigation software (v16.3), measurements were collected over 48 days between July and September 2025 along a fixed 15 km route in the Lagos metropolis on the MTN Nigeria network. Samples were recorded at 1 second intervals. Four critical key performance indicators (KPIs)—reference signal received power (RSRP), reference signal received quality (RSRQ), signal to-interference-plus-noise ratio (SINR), and received signal strength indicator (RSSI)—wereanalyzedtodeterminetheir influence on the network performance index (NPI). Correlation analysis revealed that while RSRP exhibits no sig nificant correlation with NPI during rainfall (rs = 0.009), SINR and RSRQ demonstrate strong positive correlations (rs = 0.828 and rs = 0.824, respec tively). Despite these high correlations, average performance values remained low (mean SINR = 23.72%), indicating significant rain-induced degradation. These findings provide a novel empirical basis for the development of weather aware adaptive algorithms in tropical 4G network deployments.
Towards greener telecom: energy-efficient hybrid solar–grid systems for remote base station operations Hasanah Putri; Rendy Munadi; Sofia Naning Hertiana; Alfin Hikmaturokhman
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp93-104

Abstract

Efficient and environmentally friendly energy use for base transceiver stations (BTS) in remote areas is essential for telecommunication network development. This study simulates and compares two BTS configurations: a conventional grid-powered system and a hybrid solar-grid system, focusing on energy efficiency, operational cost, and carbon emissions. The simulation was conducted over a one-year operational period using Python-based modeling with realistic input parameters. The results indicate that the hybrid system can supply approximately 74% of the annual energy demand using solar power, achieving 24.4% operational cost savings and reducing carbon emissions by 73% compared to the grid-only system. These findings confirm that the hybrid BTS system is a feasible and sustainable solution to support telecommunication expansion in remote areas with lower cost and environmental impact.
Collaborative and argumentative decision support system applied to land use planning Nawel Boudraa; Djamila Hamdadou
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp237-251

Abstract

Group decision-making in land-use planning is based on complex processes, due to the diversity of stakeholders and the plurality of criteria to be considered. This article presents the design of a collaborative group decision support system, K-ProSWOT, combining a multi-agent system and multi criteria approaches to support decision-making processes. The methodology combines the K-means clustering algorithm to group similar actions together and reduce the number of options to be studied, the Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE II) method for quantitative ranking of possible alternatives, and Strengths, Weaknesses, Opportunities, Threats (SWOT) analysis to structure qualitative collective argumentation. These tools are integrated into a participative process, culminating in a collective, well-argued decision-making process. An interactive dashboard accompanies the system, keeping track of the various stages in the decision-making process. The proposed approach aims to enhance the quality of territorial decisions by reconciling an objective assessment of data with the active involvement of stakeholders.
Evaluating hybrid and standard deep learning models for maximum temperature forecasting in a semi-arid region Oussama Zemnazi; Sanaa El Filali; Sara Ouahabi; Abderrahim Mouhtadi
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp183-193

Abstract

Temperature forecasting is important for industries affected by climate, especially in semi-arid regions where the weather can change quickly and is hard to predict over time. Many studies have examined various deep learning models, including long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural networks (CNNs), and transformer-based hybrids. However, their performance in data-limited semi-arid environments is often unclear and inconsistent. This study compares six deep learning methods for predicting daily maximum temperatures in Settat, Morocco. It uses 11 years of ground-observed meteorological data. The models examined include a baseline artificial neural network (ANN) and five hybrid structures: ANN-LSTM, ANN-GRU, ANN-CNN, ANN–random forest (RF), and ANN-transformer. The results indicate that the ANN performs the best overall, with MAE = 0.0432, root mean square error (RMSE) = 0.0543, and R² = 0.8820. It surpasses all hybrid models. When using a relative improvement metric, the ANN shows accuracy gains of 32% to 42% compared to the recurrent, convolutional, and attention-based hybrids. These results suggest that in semi-arid climates, where maximum temperature mainly depends on the same-day atmospheric conditions, simpler feedforward models work better than more complex temporal models. The study underscores the need to match model complexity with climatic factors and dataset size, offering a useful benchmark for temperature forecasting in regions with limited data.
Trophallactic optimization algorithm with markov random field refinement for stroke lesion segmentation Hayet Berkok; Karima Kies; Nacera Benamrane
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp131-141

Abstract

Cerebrovascular accidents (strokes) represent a critical medical emergency re quiring rapid and accurate diagnosis. Automated segmentation of stroke lesions from computed tomography (CT) images remains challenging due to low con trast, image noise, and high anatomical variability between ischemic and hem orrhagic subtypes. This paper introduces a novel hybrid approach combining the trophallactic optimization algorithm (TOA), inspired by cooperative nectar exchange in bee colonies, with markov random fields (MRF) for spatial coher ence modeling. The proposed TOA-MRF method operates semi-automatically from a single user-defined seed point, leveraging bio-inspired collective intel ligence to progressively explore and refine regions of interest. The algorithm simulates the enzymatic transformation of nectar into honey through iterative information exchange between virtual bees, followed by MRF-based regulariza tion to ensure anatomical consistency. Evaluated on a clinical CT dataset, the method achieves a Dice similarity coefficient of 87.3% for ischemic strokes and 91.2% for hemorrhagic strokes, with an overall detection accuracy exceeding 89%. Comparative analysis demonstrates the complemen tary strengths of TOA exploration and MRF refinement, offering a robust and efficient solution for clinical stroke assessment with minimal user intervention.
Complexity aware cascade architecture for improving user satisfaction in conversational AI Constantinus Satrio; Devi Fitrianah
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp205-214

Abstract

Conventional task-oriented chatbots frequently suffer from task incompletions and low user satisfaction when handling complex queries. This research intro duces the complexity aware cascade, an adaptive architecture that improves user service quality by dynamically matching query complexity with the appropri ate computational response. The system uses confidence and relevance scores to intelligently route requests through a sequence of a natural language under standing (NLU) model, a retrieval-augmented generation (RAG) pipeline, or a large language model (LLM). The tiered architecture was evaluated via a ran domized controlled trial (RCT) with 150 participants, measuring task success and user satisfaction. The full cascade achieved a 90% journey completion rate, representing a 92.3% improvement over baseline system and substantial gains in SERVQUAL-based service quality scores. The experiment was conducted in a domain-specific knowledge base (essential oils) with a convenience sam ple that does not represent the global population, and no real-time deployment or long-term cost analysis was performed. Accordingly, the findings should be interpreted as evidence of effectiveness in a limited setting rather than as directly scalable to all domains. Even with these limitations, this study provides arigorously tested blueprint for developing more robust and user-centric conversational AI systems.
Power-aware design-for-test: a survey of DFT techniques and scan chain reordering approaches V. Rajitha Rani; Mamatha Samson
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp30-39

Abstract

The rapid scaling of semiconductor technologies has significantly increased the integration density and introduced new categories of manufacturing defects, thereby increasing the test complexity and time. Scan-based design for-test (DFT) architectures remain the most widely adopted method for digital IC testing, where test vectors are shifted serially into and out of scan chains. Because shift operations dominate the overall test time, reducing power during scan shifting is essential to prevent IR-drop, thermal issues, reliability degradation, and potential yield loss, and to enable higher shift frequencies. A higher shift frequency directly reduces the test application time and, consequently, the overall test cost. Excessive switching during scan shift remains a significant challenge, particularly in today’s low-power devices, prompting extensive research on low-power DFT. This paper presents a structured survey of recent advancements in shift-power reduction, covering automatic test pattern generation (ATPG)-based low power test pattern generation, built-in self-test (BIST)-based low-transition pattern generation, and modern scan-chain optimization and reordering strategies. The survey highlights that among various solutions, scan chain reordering stands out as one of the most effective and scalable power-aware DFT techniques, due to its minimal implementation overhead, seamless integration with existing ATPG/BIST flows, and significant ability to reduce 20–50% scan-shift power without requiring pattern regeneration.
Improving the performance of wireless sensor network using multi-hopping clustering partition Robby Rizky; Mustafid Mustafid; Teddy Mantoro; Wahyul Amien Syafei
Indonesian Journal of Electrical Engineering and Computer Science Vol 42, No 1: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v42.i1.pp81-92

Abstract

Wireless sensor networks (WSNs) enable large-scale event monitoring; however, their performance is often constrained by low throughput. This study aims to develop a cluster-based routing protocol by implementing the multi-hopping clustering partition (MHCP) method. The MHCP process consists of three main stages: (i) cluster head (CH) selection, (ii) evaluation of node proximity to their respective CHs, and (iii) cluster partitioning to reduce intra-cluster variation. Four clusters were formed and interconnected through multi-hop communication, achieving throughput values of 142.0033, 244.1318, 119.0804, and 305.6159, respectively. In addition to the development of MHCP, the scientific contribution of this study is strengthened through the integration of the LEACH protocol and the K-means algorithm as a complementary methodological approach. LEACH improves energy efficiency through adaptive CH rotation, while K-means optimizes spatial node grouping. The combination of these methods ensures a balance between energy consumption and spatial proximity, resulting in improved throughput and extended network lifetime. Experimental results demonstrate that the proposed MHCP protocol achieves higher throughput than the conventional LEACH protocol across all clusters while maintaining acceptable delay and packet loss. These findings confirm that the integration of multi-hop communication and cluster partitioning effectively enhances data transmission efficiency and overall network performance in WSNs.

Page 922 of 923 | Total Record : 9226

 919   920   921   922   923 

Filter by Year

2012 2026


Reset
Filter By Issues
All Issue Vol 42, No 1: April 2026 Vol 41, No 3: March 2026 Vol 41, No 2: February 2026 Vol 41, No 1: January 2026 Vol 40, No 3: December 2025 Vol 40, No 2: November 2025 Vol 40, No 1: October 2025 Vol 39, No 3: September 2025 Vol 39, No 2: August 2025 Vol 39, No 1: July 2025 Vol 38, No 3: June 2025 Vol 38, No 2: May 2025 Vol 38, No 1: April 2025 Vol 37, No 3: March 2025 Vol 37, No 2: February 2025 Vol 37, No 1: January 2025 Vol 36, No 3: December 2024 Vol 36, No 2: November 2024 Vol 36, No 1: October 2024 Vol 35, No 3: September 2024 Vol 35, No 2: August 2024 Vol 35, No 1: July 2024 Vol 34, No 3: June 2024 Vol 34, No 2: May 2024 Vol 34, No 1: April 2024 Vol 33, No 3: March 2024 Vol 33, No 2: February 2024 Vol 33, No 1: January 2024 Vol 32, No 3: December 2023 Vol 32, No 1: October 2023 Vol 31, No 3: September 2023 Vol 31, No 2: August 2023 Vol 31, No 1: July 2023 Vol 30, No 3: June 2023 Vol 30, No 2: May 2023 Vol 30, No 1: April 2023 Vol 29, No 3: March 2023 Vol 29, No 2: February 2023 Vol 29, No 1: January 2023 Vol 28, No 3: December 2022 Vol 28, No 2: November 2022 Vol 28, No 1: October 2022 Vol 27, No 3: September 2022 Vol 27, No 2: August 2022 Vol 27, No 1: July 2022 Vol 26, No 3: June 2022 Vol 26, No 2: May 2022 Vol 26, No 1: April 2022 Vol 25, No 3: March 2022 Vol 25, No 2: February 2022 Vol 25, No 1: January 2022 Vol 24, No 3: December 2021 Vol 24, No 2: November 2021 Vol 24, No 1: October 2021 Vol 23, No 3: September 2021 Vol 23, No 2: August 2021 Vol 23, No 1: July 2021 Vol 22, No 3: June 2021 Vol 22, No 2: May 2021 Vol 22, No 1: April 2021 Vol 21, No 3: March 2021 Vol 21, No 2: February 2021 Vol 21, No 1: January 2021 Vol 20, No 3: December 2020 Vol 20, No 2: November 2020 Vol 20, No 1: October 2020 Vol 19, No 3: September 2020 Vol 19, No 2: August 2020 Vol 19, No 1: July 2020 Vol 18, No 3: June 2020 Vol 18, No 2: May 2020 Vol 18, No 1: April 2020 Vol 17, No 3: March 2020 Vol 17, No 2: February 2020 Vol 17, No 1: January 2020 Vol 16, No 3: December 2019 Vol 16, No 2: November 2019 Vol 16, No 1: October 2019 Vol 15, No 3: September 2019 Vol 15, No 2: August 2019 Vol 15, No 1: July 2019 Vol 14, No 3: June 2019 Vol 14, No 2: May 2019 Vol 14, No 1: April 2019 Vol 13, No 3: March 2019 Vol 13, No 2: February 2019 Vol 13, No 1: January 2019 Vol 12, No 3: December 2018 Vol 12, No 2: November 2018 Vol 12, No 1: October 2018 Vol 11, No 3: September 2018 Vol 11, No 2: August 2018 Vol 11, No 1: July 2018 Vol 10, No 3: June 2018 Vol 10, No 2: May 2018 Vol 10, No 1: April 2018 Vol 9, No 3: March 2018 Vol 9, No 2: February 2018 Vol 9, No 1: January 2018 Vol 8, No 3: December 2017 Vol 8, No 2: November 2017 Vol 8, No 1: October 2017 Vol 7, No 3: September 2017 Vol 7, No 2: August 2017 Vol 7, No 1: July 2017 Vol 6, No 3: June 2017 Vol 6, No 2: May 2017 Vol 6, No 1: April 2017 Vol 5, No 3: March 2017 Vol 5, No 2: February 2017 Vol 5, No 1: January 2017 Vol 4, No 3: December 2016 Vol 4, No 2: November 2016 Vol 4, No 1: October 2016 Vol 3, No 3: September 2016 Vol 3, No 2: August 2016 Vol 3, No 1: July 2016 Vol 2, No 3: June 2016 Vol 2, No 2: May 2016 Vol 2, No 1: April 2016 Vol 1, No 3: March 2016 Vol 1, No 2: February 2016 Vol 1, No 1: January 2016 Vol 16, No 3: December 2015 Vol 16, No 2: November 2015 Vol 16, No 1: October 2015 Vol 15, No 3: September 2015 Vol 15, No 2: August 2015 Vol 15, No 1: July 2015 Vol 14, No 3: June 2015 Vol 14, No 2: May 2015 Vol 14, No 1: April 2015 Vol 13, No 3: March 2015 Vol 13, No 2: February 2015 Vol 13, No 1: January 2015 Vol 12, No 12: December 2014 Vol 12, No 11: November 2014 Vol 12, No 10: October 2014 Vol 12, No 9: September 2014 Vol 12, No 8: August 2014 Vol 12, No 7: July 2014 Vol 12, No 6: June 2014 Vol 12, No 5: May 2014 Vol 12, No 4: April 2014 Vol 12, No 3: March 2014 Vol 12, No 2: February 2014 Vol 12, No 1: January 2014 Vol 11, No 12: December 2013 Vol 11, No 11: November 2013 Vol 11, No 10: October 2013 Vol 11, No 9: September 2013 Vol 11, No 8: August 2013 Vol 11, No 7: July 2013 Vol 11, No 6: June 2013 Vol 11, No 5: May 2013 Vol 11, No 4: April 2013 Vol 11, No 3: March 2013 Vol 11, No 2: February 2013 Vol 11, No 1: January 2013 Vol 10, No 8: December 2012 Vol 10, No 7: November 2012 Vol 10, No 6: October 2012 Vol 10, No 5: September 2012 Vol 10, No 4: August 2012 Vol 10, No 3: July 2012 More Issue