Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Filter Icon

Filters article

Years

FAQ Arrow
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

30,735 Article Results

Integration of public electric vehicle charging stations into a single gateway platform for net zero emissions goals

10.12928/telkomnika.v24i4.27786
Fajar; STMIK AMIK Bandung Sidiq Arrizal , Shafira; STMIK AMIK Bandung Febriani
The rapid adoption of electric vehicles (EVs) in Indonesia necessitates robust charging infrastructure. However, a major challenge is the highly fragmented network of public EV charging stations (SPKLU). Various operators utilize disparate protocols, resulting in isolated data silos and user range anxiety. This study proposes a nationally scalable application programming interface (API)-based gateway for cross-operator SPKLU integration. The system uses an event-driven internet of things (IoT) push mechanism. A standardized JavaScript object notation (JSON) API ensures interoperability and normalizes heterogeneous SPKLU data into a unified national dashboard. Pilot testing across 20 SPKLU locations in 10 major Indonesian cities validated cross-regional network reliability. The results demonstrate successful real-time status synchronization with a low margin of error (MoE) of 4.65%. To mitigate minor discrepancies caused by temporary network latency, a user interface (UI)-level timestamp transparency feature is proposed. Furthermore, by utilizing dynamic, region specific grid emission factors, the system accurately recorded an aggregated electricity consumption of approximately 3.5 million kWh in June 2025. This translates to an estimated 2.7 million kgCO₂eq in carbon emissions. Ultimately, this centralized platform eliminates information asymmetry for users. It also lays a crucial foundation for future smart grid integration, artificial intelligence (AI)-based demand forecasting, and Indonesia’s net zero emission (NZE) targets.
Volume: 24
Issue: 4
Page: 1113-1120
Publish at: 2026-08-01

An improved harvested energy management mechanism for wireless sensor networks

10.12928/telkomnika.v24i4.27486
Abdelmalek; University of Ibn-Khaldoun Bengheni , Messaoud; Ahmed Ben Yahia El Wancharissi University Hameurlaine
Wireless sensor networks (WSN) play a vital role in monitoring and communication applications, but their performance is often constrained by limited battery power. Energy harvesting (EH) technologies have emerged as a promising solution to extend network lifetime by supplying supplementary energy from the environment. However, efficiently balancing harvested and consumed energy remains a significant challenge. This paper introduces an improved harvested energy management mechanism (IHE2M) that dynamically adjusts the duty cycle of sensor nodes based on residual energy availability. Unlike traditional approaches that rely on fixed duty cycles, IHE2M allows each node to determine its sleep and active periods adaptively, reducing collisions, idle listening, and unnecessary retransmissions. The mechanism was evaluated through OMNeT++/MiXiM simulations and compared with existing schemes such as EH2M and dynamic source routing (DSR). Results demonstrate that IHE2M achieves higher packet delivery ratios, lower latency, and better throughput while reducing average energy consumption per node. The findings confirm that IHE2M provides a more sustainable and efficient solution for energy harvesting WSN, improving reliability and extending network lifetime.
Volume: 24
Issue: 4
Page: 1102-1112
Publish at: 2026-08-01

Decision-tree-based machine learning for detecting coffee agroforestry using SPOT-7

10.12928/telkomnika.v24i4.27747
I Made; IPB University Khrisna Yoga Devandra , I Nengah; IPB University Surati Jaya , Tatang; IPB University Tiryana
This study develops a decision-tree-based machine-learning (ML) approach to identify coffee agroforestry plants using SPOT-7 satellite imagery. The algorithm was developed by examining the combination of image indices derived from SPOT-7 and biophysical variables. Detection using spectral variables is often hampered by spectral similarity between vegetation cover classes. This study found that a ML method that combines spectral and biophysical variables can significantly improve overall accuracy, from 60.4% (using conventional spectral variables alone) to 94% (using integrated spectral-biophysical variables). For detecting and identifying agroforestry coffee classes typically found under tree canopies, the addition of the “land cover” variable published by the Ministry of Environment and Forestry contributes significantly to the classification of agroforestry coffee. Important variables identified in this model are normalized difference vegetation index (NDVI), visible difference vegetation index (VDVI), normalized red-green vegetation index (NRGI), elevation, and land cover.
Volume: 24
Issue: 4
Page: 1307-1319
Publish at: 2026-08-01

Decentralized multi-agent orchestration for legacy order-to cash optimization

10.12928/telkomnika.v24i4.27807
Rahul Kumar; University of Connecticut Thatikonda , Sucharitha; Point Park University Donepudi
Legacy enterprise resource planning (ERP) systems serve as the operational backbone of global commerce but often create bottlenecks due to their rigid, monolithic design. As organizations incorporate artificial intelligence (AI), these outdated systems struggle to support high-speed, parallel workflows, creating a significant integration challenge. This paper introduces a non intrusive modernization approach that overlays a decentralized multi-agent system (MAS) onto existing infrastructure without requiring invasive code changes. By developing a digital twin of the order-to-cash (O2C) process, we train autonomous agents through multi-agent reinforcement learning (MARL) to manage credit validation, inventory allocation, and fulfillment. We adapt the centralized training, decentralized execution (CTDE) framework to meet O2C constraints, enabling agents to learn globally optimal strategies while operating independently. Simulation results show that this architecture surpasses rule-based robotic process automation (RPA) baselines, increasing total throughput by 6.9% over a monolithic setup, though at a 6.3% error rate due to aggressive allocation policies. These results indicate that decentralized agent-based orchestration provides a scalable approach for modernizing legacy ERPs, offering increased agility without the risks associated with platform replacement.
Volume: 24
Issue: 4
Page: 1216-1223
Publish at: 2026-08-01

Design and evaluation of a simple load balancing prototype using the round robin algorithm in local networks

10.12928/telkomnika.v24i4.27560
Muh. Fahmi; Universitas Sulawesi Barat Rustan , Wawan; Universitas Sulawesi Barat Firgiawan , Wiwi; Universitas Sulawesi Barat Nopiana
Load balancing plays a crucial role in ensuring efficient workload distribution and maintaining stable performance in web service systems. This study presents the design and experimental evaluation of a round robin–based load balancing system implemented in a multi-client local area network (LAN) environment using NGINX as a centralized controller. The system consists of three physical machines, comprising one load balancer and two backend servers hosting identical web applications. Multiple clients generate simultaneous hypertext transfer protocol (HTTP) requests, which are distributed alternately to the backend servers using the default round robin mechanism provided by NGINX. Experimental evaluation was conducted under three workload scenarios of 50, 100, and 200 concurrent requests. The results show that the round robin algorithm consistently distributes requests evenly between the backend servers. The average response time increased from approximately 110 ms at 50 requests to 165 ms at 100 requests and 290 ms at 200 requests, indicating stable performance under light to moderate load conditions. These findings demonstrate that the proposed system is lightweight, modular, and easy to deploy in resource limited environments. The implementation is particularly suitable for campus-scale networks and small institutional settings, serving as a practical platform for local server deployment, academic applications, and experimental learning in networking and distributed systems.
Volume: 24
Issue: 4
Page: 1121-1130
Publish at: 2026-08-01

Spatial and channel attention mechanism for speech disfluency detection using deep learning technique

10.11591/ijece.v16i4.pp2106-2119
Kusuma H. R. , G. Seshikala
Stuttering is a speech communication disorder, it is characterized by repetitions, prolongation, and unusual pauses that cause interference with the natural flow of speech. In recent times, automatic speech recognition and speech processing systems have gained enormous attention because they are used in most of the human machine interaction applications. However, the performance of these systems is affected by stutter speech, stutter detection is the major challenge due to speech disfluencies. To address this major challenge, this paper introduced a novel deep learning (DL) based paradigm, which integrates a hybrid feature extraction algorithm, with the Spatial and Channel attention mechanism to refine the features and for reliable detection of speech disfluency. This study is conducted on multiple stutter data set which includes UCLASS (Release 1, Release 2), FluencyBank and SEP-28k. The major drawback of all these data sets is data imbalance. To reduce this imbalance, the author used data augmentation techniques, which includes, noise, music, reverberation and pitch shifting methods. However, increasing the stutter detection accuracy remains a challenging issue. To address this issue, the author proposed a hybrid feature extraction model, which extracts temporal, contextual, spectral, and pitch information from the speech signal. The obtained features are then processed through the attention mechanism where channel and spatial attention models help to refine the features. Finally, a multiclass convolutional neural network (CNN) classifier is used to detect the stutter event in the speech signals. The results show that our model with spatial and channel attention mechanism performs better than existing deep learning approaches and accurately detects stuttering.
Volume: 16
Issue: 4
Page: 2106-2119
Publish at: 2026-08-01

A comparative study of baseline convolutional neural network and ResNet50 for image-based tomato leaf disease classification

10.11591/ijece.v16i4.pp1876-1884
Sumana Budsabok , Wachiraporn Polpanumas , Piyanan Khongphai
Image-based techniques are widely used in plant disease classification to support agricultural productivity and facilitate early detection. This study presents a comparative analysis between a baseline convolutional neural network (CNN) and a ResNet50-based transfer learning model for tomato leaf disease classification. A publicly available dataset containing five categories—tomato bacterial spot, tomato late blight, tomato septoria leaf spot, tomato yellow leaf curl virus, and healthy leaves—was used in the experiments. Model performance was evaluated using several standard classification metrics, with emphasis on overall accuracy. The baseline CNN achieved an accuracy of 97.0%, whereas the ResNet50 model reached 99.6%. The results demonstrate that the ResNet50 model produces more stable and reliable predictions, particularly when distinguishing between visually similar disease classes. These findings confirm that transfer learning can effectively improve classification performance in plant disease recognition tasks.
Volume: 16
Issue: 4
Page: 1876-1884
Publish at: 2026-08-01

Teaching analysis of sub-synchronous resonance of thermal power plants using virtual laboratory

10.11591/ijece.v16i4.pp1677-1687
Sugiarto Kadiman , Ratna Kartikasari
The development of a MATLAB/Simulink-based virtual laboratory for studying sub-synchronous resonance (SSR) offers a robust educational platform for analyzing complex power system interactions. Based on the IEEE first benchmark model, this virtual environment provides a safe, efficient, and comprehensive tool for engineering students to study the dangerous interactions between series-compensated lines and turbo-generator shaft systems. The simulation features a 920 MVA, 60 Hz turbo-generator connected to an infinite bus through a series-compensated line. Students can analyze torsional interaction, which result from energy exchange between the electrical network and the mechanical shaft. Higher degrees of series compensation increase the risk of SSR, as the electrical resonant frequency matches the complement of one of the mechanical shaft torsional modes.
Volume: 16
Issue: 4
Page: 1677-1687
Publish at: 2026-08-01

Motivational and normative drivers of generative AI substitution in academic work: a mixed-methods study from Saudi higher education

10.11591/ijere.v15i4.38745
Mazin Mansory , Zilal Meccawy
The rapid integration of generative artificial intelligence (GenAI) in higher education has intensified tensions between legitimate learning support and unauthorized task substitution, particularly where institutional guidance remains ambiguous. This mixed-methods study investigates how attitudes toward AI, moral rationalization strategies, and perceived institutional clarity interact to shape AI-based substitution behavior among 249 undergraduates at a Saudi university. Partial least squares structural equation modeling (PLS-SEM) revealed that positive attitudes and rationalization together explained 46% of the variance in substitution behavior, with perceived clarity of institutional guidance significantly moderating the rationalization–substitution link. Complementary interviews with seven students and ten instructors revealed that linguistic burden, peer norms, and fragmented faculty guidance facilitated boundary crossing from scaffolding to shortcutting. By exploring the relationship between moral neutralization and environmental clarity, this research offers a new approach to evaluating the effectiveness of institutional AI guidance beyond common technology acceptance models. The findings can be used to inform the design of multi-tiered, inclusive AI usage policies, assessments that value process over product, and culturally responsive academic integrity education within a multilingual higher education context.
Volume: 15
Issue: 4
Page: 2946-2958
Publish at: 2026-08-01

Beyond narrative: a pedagogical, cultural, and psychological analysis of Saken Zhunusov’s Amanai and Zamanai for higher education

10.11591/ijere.v15i4.38486
Tokzhan Igenbay , Gauhar Baltabaeva , Amangaisha Bolsynbayeva , Gulnara Apeyeva , Sarash Konyrbayeva
This study offers a comprehensive pedagogical analysis of Saken Zhunusov’s Amanai and Zamanai, demonstrating that the novella functions as a multilayered educational text suitable for literature, cultural studies, teacher education, and psychology-of-literature curricula in higher education. Using qualitative content analysis, the study identifies six interrelated thematic domains; moral education, cultural learning, developmental psychology, folklore pedagogy, narrative methodology, and emotional literacy, through which the novel teaches readers to interpret emotional, ethical, and cultural meanings embedded in the narrative. The data consisted of the full text of Saken Zhunusov’s Amanai and Zamanai, analyzed using qualitative content analysis. Findings reveal that the text models moral dilemmas, cultivates empathy, preserves Kazakh cultural knowledge, exposes structural inequalities, and illustrates childhood cognition and trauma through symbolic and myth-infused storytelling. The study connects these themes to established theoretical perspectives including Vygotsky’s symbolic mediation, Bruner’s narrative cognition, Rosenblatt’s reader–response theory, and cultural-historical views of oral tradition. By developing a detailed codebook and pedagogical framework, the research provides a replicable model for analyzing culturally embedded literature and demonstrates the relevance of Amanai and Zamanai to contemporary Kazakh social issues such as poverty, gendered burden, and generational trauma. The study concludes that the novel offers rich opportunities for interdisciplinary teaching and contributes significantly to the integration of Kazakh literature into modern higher education pedagogy.
Volume: 15
Issue: 4
Page: 3591-3603
Publish at: 2026-08-01

Comparative performance analysis of lightweight face identification algorithm

10.11591/ijece.v16i4.pp2042-2060
Wuyun Wang , Suchada Sitjongsataporn
With the wide application of face recognition in resource-constrained scenarios like mobile and embedded devices, lightweight algorithms have become a research focus, but existing studies lack multi-dimensional, scenario-based performance comparisons. This paper studies the performance evaluation and application adaptation of lightweight face recognition algorithms, innovatively builds a scenario-based evaluation system, verifies the performance improvement of combining traditional algorithms with MobileNet, and constructs an efficient, stable and low-cost system. It elaborates on face recognition principles, including key links of face detection, feature extraction and matching, introduces traditional algorithms such as Eigenfaces, Fisherfaces and LBPH, and focuses on MobileNet’s characteristics: reducing computation and parameters via depthwise separable convolution, and adjustable width and resolution. Four comparative experiments verify the "traditional algorithms + MobileNet" hybrid strategy. Results show the combination achieves 98.1% accuracy, 4.3 percentage points higher than single MobileNet; LBPH + MobileNet balances performance and resource consumption best, with 110MB memory, 40% CPU usage and 315ms processing time. The hybrid strategy improves accuracy and efficiency in different scenarios, aiming to provide a scientific basis for the engineering application and subsequent optimization of lightweight face recognition algorithms, and supporting algorithm selection and performance improvement in resource-constrained scenarios.
Volume: 16
Issue: 4
Page: 2042-2060
Publish at: 2026-08-01

Implementation of support vector machine on LVMDP panel with overheating protection system

10.11591/ijece.v16i4.pp1755-1766
Annas Singgih Setiyoko , Dimas Pristovani Riananda , Adianto Adianto
Electricity is a critical requirement in industrial operations, where the continuity and stability of power distribution directly affect safety and productivity. The low voltage main distribution panel (LVMDP) functions as the main node of electrical power distribution; however, conventional LVMDP systems generally lack intelligent protection mechanisms capable of detecting overheating-related fire hazards and initiating preventive action before failure occurs. This study proposes an intelligent monitoring and protection system for LVMDP panels that combines real-time multi-sensor monitoring, support vector machine (SVM)-based hazard classification, and an automatic shutdown mechanism. The main contribution of this work lies in the integration of predictive thermal risk detection with autonomous protective action, enabling the system not only to monitor panel conditions but also to respond immediately to hazardous states before they escalate into fire incidents. SVM was selected because of its strong capability to classify complex and nonlinear patterns from sensor data with high reliability. The developed system continuously evaluates panel conditions and triggers auto-shutdown when an overheating risk is identified, thereby improving preventive protection compared with conventional alarm-based monitoring systems. Experimental results show that the sensor measurements achieved error rates mostly below 5% compared with calibrated instruments, indicating good accuracy. In addition, the SVM model obtained an overall accuracy of 93%, with a macro-average F1-score of 92% and a weighted-average F1-score of 93%. These results demonstrate that the proposed system is effective for early detection and active protection of LVMDP panels against overheating hazards.
Volume: 16
Issue: 4
Page: 1755-1766
Publish at: 2026-08-01

Real-time anomaly detection system using best performed machine learning model

10.12928/telkomnika.v24i4.27561
Victor; North-West University Mathebula , Bukohwo; North-West University Michael Esiefarienrhe
Effective anomaly detection is critical for protecting organizational networks against increasingly sophisticated cyber threats. However, most machine learning-based intrusion detection models are developed and validated using public benchmark datasets, which may not reflect the operational characteristics, traffic behavior, and threat patterns of real institutional networks. In the case of Umalusi, there is currently no anomaly detection model customized and validated using Umalusi-specific network traffic, creating a practical gap in deployable cybersecurity capability. This study proposes a hybrid machine learning framework tailored to support accurate, efficient, and operationally relevant anomaly detection. Using knowledge discovery in databases (KDD) process, network traffic data were collected and pre-processed through normalization, label encoding, missing value treatment, and dimensionality reduction using principal component analysis (PCA). The 16 hybrid models integrating unsupervised anomaly detection with supervised classification were implemented and comparatively evaluated. Experimental findings indicate that the density-based spatial clustering of applications databasescan (DBSCAN) + random forest (RF) model achieved 99.92% accuracy while maintaining a low false positive (FP) cost, making it suitable for a security operations centre (SOC). In addition, a Flask-based web application was developed to enable real-time deployment by sniffing live network traffic, executing inference, and persisting results in an SQLite database.
Volume: 24
Issue: 4
Page: 1204-1215
Publish at: 2026-08-01

Predictive safety helmet for miners using internet of things and artificial intelligence

10.12928/telkomnika.v24i4.27421
Vijayalakshmi; Thiagarajar College of Engineering Murugesan , Irudhaya Ronisha Innasi; Thiagarajar College of Engineering John Benedict , Janani; Thiagarajar College of Engineering Vigneswaran , Pooja; Thiagarajar College of Engineering Senthamarai Kannan
Mining is still responsible for many deaths since mines have dangerous environmental conditions including mine collapses, gas emissions, and high temperatures. However, traditional helmets do not provide adequate protection; besides, they cannot analyze miners’ health as well as the environmental hazards. In order to solve this issue, this work presents a predictive safety helmet equipped with several sensors and means of communication. Specifically, the helmet comprises a micro-electro mechanical systems (MEMS) accelerometer for vibration monitoring, a gas sensor for detecting the presence of harmful gases, a heartbeat sensor for assessing workers’ well-being, and a temperature sensor for monitoring the environmental parameters. Additionally, the device is provided with a global positioning system (GPS) module for location determination and a global system for mobile (GSM) module for transmitting alert notifications in case of emergency situations. The collected data is analyzed on an internet of things (IoT)-based system; any signs of danger cause alerts to be sent immediately.
Volume: 24
Issue: 4
Page: 1177-1186
Publish at: 2026-08-01

Behavioral fingerprints: driver profiling using transformer models on next generation simulation trajectory data

10.12928/telkomnika.v24i4.27790
Mohamed; Abdelmalek Essaadi University Laamimach , Mghari; Abdelmalek Essaadi University Mohammed , Aziz; Abdelmalek Essaadi University Mabrouk
Characterizing individual driver behavior is essential for advancing intelligent transportation systems (ITS) and autonomous vehicle safety. While deep learn ing models excel at macroscopic traffic prediction, individual driving styles are often aggregated away. This paper addresses this gap by proposing a novel, weakly supervised transformer framework for driver behavior profiling using high-resolution next generation simulation (NGSIM) US-101 trajectory data. We extract microscopic behavioral features including acceleration, lane change dynamics, and headway management from 30-second observation segments. A transformer encoder learns complex temporal dependencies to classify drivers into ’aggressive’ and ’normal’ profiles, achieving a 97% F1-score on proxy labeled segments. Crucially, these “proxy labels” are derived from heuristic statistics, meaning the model is trained to learn the mapping from sequences to these behavioral indicators rather than identifying objective aggression. Our methodology enables the creation of precise “behavioral fingerprints” that cap ture individual driving nuances. These insights are vital for developing adaptive ITS that anticipate traffic stability issues and enhance autonomous vehicle safety by predicting human intent.
Volume: 24
Issue: 4
Page: 1168-1176
Publish at: 2026-08-01
Show 6 of 2049

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration