Articles

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

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,456 Article Results

Business intelligence for measuring global systems for mobile communication provider performance

10.12928/telkomnika.v24i2.26293
Yusri Eli Hotman; Universitas Trisakti Turnip , Dedy; Trisakti University Sugiarto , Rina; Universitas Trisakti Fitriana , Yun-Chia; Yuan Ze University Liang
Internet access is getting easier in various places, including Indonesia. Telecommunication media are no longer dominated by the use of pulse signals but have shifted to relying on internet access. This study aims to create a data visualization of internet speed in Bekasi urban sub-districts using the business intelligence (BI) model with online analytical processing (OLAP). Clustering was carried out using two methods, namely the K-means and K-medoids methods which were selected based on the Davies Bouldin index (DBI) value. This study produced a visual data prototype from the results of clustering from the data mining process and was accompanied by supporting data in the form of information on the highest and lowest speeds in the studied sub-districts. The clustering process uses K-means for uploading data with a DBI value of 0.847, while the data download uses K-medoids with a DBI value of 0.871. The prototype displays observation data, maximum and minimum value information, and the clustering result. The functional test result for the prototype showed conformity with the requirements, while the validation test showed that the prototype passed the validation test with a score of 0.8833.
Volume: 24
Issue: 2
Page: 737-750
Publish at: 2026-04-01

Hybrid intrusion detection in IoT devices: a deep learning approach using Kitsune and quantized autoencoder

10.12928/telkomnika.v24i2.27316
Md. Rifat E; Comilla University Noor , Md. Tofael; Comilla university Ahmed , Dulal; Comilla University Chakraborty , Pintu Chandra; Comilla University Paul , Sohana; Comilla University Nowar , Rejwan; Comilla University Ahmed , Tanjina; Comilla University Akter
Internet of things (IoT) has been transforming the way to connect and communicate in smart homes, healthcare, and businesses so fast and rapidly around the world. But this growth has complicated security, because IoT devices are more likely to be hacked as they’re smaller, without even regular security practices, and under attack by more sophisticated threats. Traditional intrusion detection systems (IDS) are not functioning well in IoT environments as they are computationally expensive and struggle to accommodate the heterogeneous nature of IoT networks. This paper introduces a cross-domain intrusion detection based on adaptive adversarial training using Kitsune and quantized autoencoders (QAE) for anomaly detection and classification. The model is capable of capturing different attacking techniques, such as distributed denial of service (DDoS), Mirai botnet attacks, address resolution protocol (ARP) spoofing, and data exfiltration, by leveraging the reconstruction error generated by Kitsune autoencoders. The degree-based classification enables the system to dynamically categorize anomalies according to their severity, rendering the model exceptionally adaptive to various attacks. The anomalies are also classified into different types of attacks (normal, suspicious, and malicious) based on binarized error values. The approach achieves a high accuracy with an F1 score of 85.9% and supports real-time characterization to increase security in IoT scenarios.
Volume: 24
Issue: 2
Page: 452-465
Publish at: 2026-04-01

Noise-suppression method for UAV-OFDM systems by introducing CV-VSS-NLMS algorithm and single-antenna architecture

10.12928/telkomnika.v24i2.27396
Walid; Université Abbes Laghrour Khenchela Lebbou , Laid; Université Abbes Laghrour Khenchela Chergui , Saad; Setif 1 University Ferhat Abbas Bouguezel
In this paper, we address the critical challenge of impulsive interference in orthogonal frequency division multiplexing (OFDM)-based unmanned aerial vehicle (UAV) communication systems, which can severely degrade data transmission reliability. Specifically, we propose a novel complex-valued variable step-size normalized least mean square (CV-VSS-NLMS) adaptive filtering algorithm dedicated for adaptive filtering of complex-valued signals, providing real-time, lightweight, and efficient impulsive-noise suppression for UAV-OFDM signals. In contrast, real-valued VSS-LMS filters treat the real and imaginary parts separately, resulting in poorer mean square error (MSE) convergence for complex signals. The algorithm is developed by efficiently adapting LMS-based filtering strategies to impulsive interference scenarios and adequately integrating prior concepts of electromagnetic pulse suppression within a well-designed single-antenna UAV architecture. This new configuration is especially suited for size, weight, and power-constrained UAV platforms, where reducing complexity is highly desirable. In contrast to conventional blind source separation approaches, the proposed solution ensures reliable communication without excessive processing demands, since it efficiently suppresses impulsive noise and greatly reduces the number of matrix operations. Simulation results demonstrate a significant improvement in bit error rate (BER), confirming that the proposed CV-VSS-NLMS technique provides a robust, dependable, and practical solution for modern UAV communication links.
Volume: 24
Issue: 2
Page: 407-419
Publish at: 2026-04-01

Deep neural network classification in chatbot system family health counseling services

10.11591/ijai.v15.i2.pp1211-1218
Andi Riansyah , Sam Farisa Chaerul Haviana , Ratna Supradewi , Muhammad Ainul Wahib
Mental health problems affect many aspects of life, including physical well being, work productivity, social functioning, and suicide risk. In Indonesia, access to professional mental health services remains very limited: only a small proportion of people with depression receive treatment and the number of mental health professionals per population is far below international recommendations, creating an urgent service gap. This study proposes an artificial intelligence–based chatbot to support family mental health counseling services in Indonesia. The chatbot uses a deep neural network (DNN) to classify user questions into counseling intent categories and to provide appropriate responses. Psychologists compiled and verified a dataset of Indonesian counseling questions and responses, which was then pre processed using standard text processing techniques and encoded with a bag of words (BoW) representation. A fully connected DNN with one input layer, two hidden layers of eight neurons each, and a SoftMax output layer was trained using the Adam optimizer (learning rate 0.01) on 80% of the data and evaluated on the remaining 20%. The best configuration achieved a training accuracy of 96%, with test results of 93% accuracy, 92% precision, 93% recall, and 92% F1-score. These findings indicate that proposed DNN based chatbot can accurately classify counseling intents and generate contextually appropriate responses, suggesting its potential as complementary tool to support initial family mental health counseling in Indonesia.
Volume: 15
Issue: 2
Page: 1211-1218
Publish at: 2026-04-01

System dynamics control simulation for sustainability of Indonesia’s cocoa supply chain

10.12928/telkomnika.v24i2.27509
Imam; Universitas Brawijaya Santoso , Dodyk; Universitas Brawijaya Pranowo , Hendrix Yulis; Universitas Brawijaya Setyawan , Izzum; Universitas Brawijaya Wafi'uddin , Naila Maulidina; Universitas Brawijaya Lu'ayya , Annisa'u; Politeknik Negeri Jember Choirun
Indonesia’s cocoa sector faces challenges in greenhouse gas emissions and smallholder income volatility. This study develops a system dynamics model to simulate the interrelationship between carbon emissions and economic performance across the cocoa value chain, identify leverage points, and evaluate alternative policy scenarios. The model integrates environmental and economic variables into dynamic feedback structures, enabling scenario-based assessment of intervention strategies. Five scenarios were simulated: composting cocoa waste increased farmer income by 2% and reduced farm-level emissions from 0.43 to 0.303 kg CO₂-eq/kg (29.79% total reduction); biogas conversion raised income by 13.56% and reduced emissions by 11%; converting cocoa waste into animal feed slightly increased income by 0.23% while cutting emissions by 58.6%; combining composting with improved transport efficiency reduced emissions by 14%; and integrating composting, logistics optimization, and government-supported input subsidies yielded the highest performance, with a 13.50% income increase and a 70% emission reduction. These results demonstrate that integrated, system-based interventions can enhance both economic resilience and environmental sustainability. The system dynamics model provides policymakers and supply chain actors with actionable insights for designing effective, climate-aligned strategies in Indonesia’s cocoa industry.
Volume: 24
Issue: 2
Page: 431-451
Publish at: 2026-04-01

Applications of artificial intelligence in analyzing Aquilaria essential oils: a review of current machine learning techniques

10.11591/ijai.v15.i2.pp1087-1096
Noor Aida Syakira Ahmad Sabri , Nur Athirah Syafiqah Noramli , Muhammad Ikhsan Roslan , Nurlaila Ismail , Zakiah Mohd Yusoff , Ali Abd Almisreb , Mohd Nasir Taib
This study explores the application of machine learning (ML) techniques in the classification of agarwood oil, focusing on the use of various algorithms such as k-nearest neighbors (KNN), support vector machines (SVM), random forest (RF), and artificial neural networks (ANN). Since 2013, ML has played a pivotal role in analyzing agarwood oil, particularly by leveraging data from a variety of chemical compounds found in the Aquilaria genus. Through a systematic review and bibliometric analysis using the SCOPUS database, this study compiles and highlights recent works that have successfully employed ML techniques for the quality assessment of agarwood oil. These studies utilize chemical data, such as gas chromatography-mass spectrometry (GC-MS) and nuclear magnetic resonance (NMR), for the classification and detection of different oil grades. The review reveals a broad range of ML applications, demonstrating their growing importance in the field of essential oil analysis. By systematically presenting the findings from recent research, this work emphasizes the potential for further exploration of ML in the standardization and improvement of agarwood oil classification techniques.
Volume: 15
Issue: 2
Page: 1087-1096
Publish at: 2026-04-01

Design of vehicle to vehicle communication: accident collision prevention using light fidelity and wireless fidelity technology

10.12928/telkomnika.v24i2.27570
Folashade Olamide; Landmark University Omua-ran Nigeria Ariba , Yusuf Isaac; Landmark University Omu-Aran Onimisi , Adedotun; Landmark University Omu-Aran Ijagbemi , Dickson Ogochukwu; Landmark University Omu-Aran Egbune
Vehicle-to-vehicle (V2V) communication is a key component of intelligent transportation systems (ITS), enabling seamless data exchange between vehicles to limit collision risks. This study presents a hybrid communication framework that integrates light fidelity (LiFi) and wireless fidelity (WiFi) technologies to enhance safety and reliability in accident prevention. Lifi using visible light communication, provides line-of-sight for short-range communication, while WiFi ensures long-range coverage in dynamic traffic environments. The proposed system allows vehicles to share speed, braking, and positional data, enabling timely warnings to drivers in high-risk scenarios. The system fuses data communication protocol design, simulation, prototype development, testing, and evaluation. The prototype model was designed and simulated to evaluate the performance of the system in terms of functionality, timing and reliability. Results indicate that the hybrid LiFi-WiFi system improves data transmission efficiency and reduces delay compared to standalone wireless systems. This approach demonstrates significant potential in developing safer transportation networks by combining complementary wireless technologies for V2V communication.
Volume: 24
Issue: 2
Page: 396-406
Publish at: 2026-04-01

Performance assessment of an adaptive model predictive control with torque braking for lane changes

10.12928/telkomnika.v24i2.27167
Zulkarnain; Universitas Sriwijaya Zulkarnain , Irwin; Universitas Sriwijaya Bizzy , Armin; Universitas Sriwijaya Sofijan , Mohd Hatta Mohammed; Universiti Teknologi Malaysia Ariff
The growing demand for autonomous vehicles requires robust control systems that can maintain safety during complex maneuvers like lane changes. However, a significant research gap exists in developing controllers that effectively manage the combined challenges of steering and braking across diverse and unpredictable driving conditions, such as varying speeds and low-friction road surfaces. This research addresses this gap by proposing and evaluating an adaptive model predictive control (MPC) system integrated with a torque braking distribution strategy. The key advantage of our adaptive method is its ability to continuously update its internal model in real-time, allowing it to anticipate and respond to changing road friction and vehicle dynamics more effectively than a static controller. In simulations of a lane change maneuver across speeds of 10-25 m/s and road friction levels from 0.3 (icy) to 1 (dry asphalt), the proposed system demonstrated a substantial performance improvement. The proposed framework demonstrated a 52.8% average reduction in lateral tracking error and enhanced stability by reducing the yaw rate by up to 41.8% on low-friction surfaces, compared to a non-adaptive MPC baseline. These results quantitatively confirm that our framework’s synergistic coordination of steering and braking significantly enhances the safety, precision, and reliability of autonomous lane change maneuvers.
Volume: 24
Issue: 2
Page: 696-706
Publish at: 2026-04-01

Evaluating learning rate effects on long short-term memory for Indonesian sentiment classification

10.12928/telkomnika.v24i2.27398
Serly; Universitas Maritim Raja Ali Haji Eldina , Tekad; Universitas Maritim Raja Ali Haji Matulatan , Novrizal Fattah; Universitas Maritim Raja Ali Haji Fahmitra
Hyperparameter optimization is a crucial process for enhancing the performance of deep learning models, particularly in the context of Indonesian sentiment classification. This study examines the impact of varying learning rates on a long short-term memory (LSTM) architecture trained with the adaptive moment estimation (Adam) optimizer. The dataset comprises 9,295 Indonesian comments automatically labeled by the Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT) model. Stratified k-fold cross-validation was employed to maintain class balance during training. Learning curves were analyzed to evaluate convergence and identify potential overfitting, while early stopping was applied when performance improvements became insignificant. The one-way analysis of variance (ANOVA) test (p-adj = 0.000575 < 0.05) revealed significant differences among the learning rate variations. Post-hoc analysis indicated the learning rates of 0.0001, 0.001, and 0.002 differ significantly from 0.02. Descriptive statistics showed that a learning rate of 0.001 was the most optimal, achieving the highest validation accuracy while maintaining a relatively low variance. Evaluation across two data categories demonstrated that lower learning rates (0.0001 and 0.002) achieved the best accuracy, 78.71% on in-domain data, whereas higher learning rates (0.01 and 0.02) performed better on cross-domain data with 36% accuracy. These findings highlight the crucial role of learning rate selection in determining model stability and generalization capability.
Volume: 24
Issue: 2
Page: 564-573
Publish at: 2026-04-01

The impact of EPS on procurement performance: the mediating role of supplier relationship quality in Ghana

10.12928/telkomnika.v24i2.27514
Isaac; University of Professional Studies, Accra - Ghana Asampana , Felix Acquah; Public Procurement Authority Baiden
This study examines the effect of e-procurement systems on procurement performance (PP) in Ghana, highlighting the mediating role of supplier relationship quality (SRQ). A quantitative, cross-sectional survey of 370 procurement professionals from public and private organisations was conducted to assess four dimensions of e-procurement: system integration, data transparency, user-friendliness, and automation. Results indicate that all four dimensions significantly enhance PP, with system integration and user-friendliness emerging as the strongest predictors. Mediation analysis further reveals that SRQ, characterised by trust, communication, and collaboration, partially strengthens the relationship between e-procurement and procurement outcomes. Nonetheless, challenges such as inadequate staff training, limited supplier digital skills, weak infrastructure, and insufficient managerial support hinder optimal system effectiveness. Grounded in the resource-based view (RBV) and transaction cost economics (TCE), the study demonstrates the importance of combining technological and relational capabilities. Recommendations include enhancing digital skills training, strengthening supplier engagement, improving system design, and fostering institutional support.
Volume: 24
Issue: 2
Page: 490-499
Publish at: 2026-04-01

A counter-centric binary-to-binary coded decimal and multiplexed seven-segment driver on an Artix-7 FPGA

10.12928/telkomnika.v24i2.27610
Ahmed Mohamed Abdellatif Abdelrahman; King Abdulaziz University Elngar , Muhamad S.; King Abdulaziz University Mauladdawilah , Tariq H. M.; King Abdulaziz University Alomary
This paper presents a complete field-programmable gate array (FPGA) implementation for showing a 4-bit binary value (0–15) as a two-digit decimal number on the Nexys-4 double data rate (DDR) seven-segment display. The design comprises: (i) a compact binary-to-binary-coded decimal (BCD) converter tailored to the 0–15 range; (ii) a seven-segment decoder for active-low, common-anode digits; and (iii) a counter-based clock-enable controller that time-multiplexes the digits at a rate chosen to be flicker-free yet energy-efficient. A simple timing model links the divider width , the number of digits , and the refresh rate . Simulation verified hazard-free switching and one-hot anode selection; hardware tests on the Nexys-4 DDR (100 MHz clock) confirmed the analysis. Selecting  yields  ms and  Hz, which removes ghosting while avoiding unnecessary high-frequency scanning. The system displays all inputs correctly and provides a clear sizing rule for wider inputs and more digits. The approach is fully synthesizable, resource-light, and portable to larger word-lengths and displays.
Volume: 24
Issue: 2
Page: 676-684
Publish at: 2026-04-01

Attributes conducive to anthropomorphism in artificial intelligence

10.12928/telkomnika.v24i2.27483
Rizwan; Murray State University Syed , Hassan; Murray State University Mistareehi
The rapid development of artificial intelligence (AI), particularly large language models (LLMs), has generated both enthusiasm and concern regarding its role in society. While these systems demonstrate impressive technical capabilities, public acceptance is often hindered by perceptions of unpredictability, mistrust, and fears amplified by media narratives. One potential strategy to improve user acceptance is anthropomorphism, the attribution of human-like qualities to AI systems which can make interactions feel more natural and trustworthy. This paper investigates the attributes most conducive to anthropomorphism by conducting a structured review across psychology, human-robot interaction, communication studies, and business applications. The analysis identifies key traits such as emotional expressiveness, conversational coherence, adaptive social behavior, and role-based framing that enhance perceptions of AI as relatable and dependable. By synthesizing these insights, we propose a conceptual framework that highlights the psychological, social, and technical dimensions of anthropomorphism in AI. The findings provide guidance for designing AI systems that balance efficiency with user trust, thereby supporting more effective integration of AI into business, research, and everyday life.
Volume: 24
Issue: 2
Page: 588-598
Publish at: 2026-04-01

Explainable social media disaster image classification using a lightweight attention-based deep learning approach

10.11591/ijai.v15.i2.pp1464-1472
Rashmi Kangokar Taranath , Geeta Chidanandappa Mara
In recent years, the rapid dissemination of social media content during natural and man-made disasters has created a need for automated and accurate disaster image classification systems. This paper proposes lightweight explainable attention-based disaster network (LEAD-Net), a deep learning (DL) model designed for classifying disaster-related images with high accuracy and interpretability. The system integrates an EfficientNet-B0 backbone enhanced with squeeze-and-excitation (SE) attention modules and a lightweight neural architecture search (NAS-lite) strategy for tuning the classifier head and training hyperparameters. The model was evaluated on two benchmark datasets comprehensive disaster dataset (CDD) and damage multimodal dataset (DMD) achieving 96% and 87% accuracy, respectively, outperforming several established convolutional neural network (CNN) baselines. To ensure transparency, gradient-weighted class activation mapping (Grad-CAM) was employed to generate visual explanations of the model’s decisions, confirming its focus on semantically relevant image regions.
Volume: 15
Issue: 2
Page: 1464-1472
Publish at: 2026-04-01

Dynamic pooling using average-thresholding to improve image classification performance

10.12928/telkomnika.v24i2.27619
Pajri; President University Aprilio , Tjong Wan; President University Sen
Pooling layers are essential in convolutional neural networks (CNNs) for reducing data size while preserving key features. Traditional methods such as Max and Average pooling have limitations. Max pooling is sensitive to noise, while Average pooling treats all activations equally. Although T-Max-Avg pooling addresses these limitations through adaptive top-k selection, its rigid decision rule requires multiple threshold comparisons and limits efficiency, motivating a simpler decision mechanism. This study introduces average-thresholding pooling (ATP), a simplified adaptive method that replaces multiple threshold comparisons with a single decision based on the average of the top-k activations. This design improves computational efficiency and reduces sensitivity to outliers. Experiments on the STL-10 dataset using a LeNet-5 architecture show that the proposed method achieves accuracy comparable to T-Max-Avg pooling (~55.5%) while consistently improving both training efficiency and inference speed. These results indicate that ATP provides a lightweight and practical alternative for CNN-based image classification, offering an improved balance between classification performance and computational efficiency.
Volume: 24
Issue: 2
Page: 663-675
Publish at: 2026-04-01

The effects of data imbalance on fraud detection model accuracy

10.11591/ijai.v15.i2.pp1402-1408
Rusma Anieza Ruslan , Nureize Arbaiy , Pei-Chun Lin
Machine learning (ML) model performance is often assessed by accuracy, but the quality and balance of data also play crucial roles. Imbalanced datasets, where the minority class has fewer samples than the majority class, can lead to biased predictions favoring the majority class. This study addresses the issue of class imbalance through resampling techniques, including random undersampling (RUS) and random oversampling (ROS), specifically applied to a fraud detection dataset. We classify the resampled datasets using random forest (RF) and gradient boosting (GB) models. Our findings indicate that the RF model, when combined with ROS, achieves an accuracy of 97.4%, surpassing the 96.1% accuracy of the GB model with RUS. This approach demonstrates the importance of addressing class imbalance to improve prediction accuracy in ML.
Volume: 15
Issue: 2
Page: 1402-1408
Publish at: 2026-04-01
1 2 3
...
2097 2098
Show 107 of 2098

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