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

30,376 Article Results

Quantitative evaluation of a virtual tour navigation system using satisfaction modeling: a case study in Thai cultural tourism

10.11591/ijeecs.v41.i2.pp690-699
Ekapong Nopawong , Rawinan Praditsangthong
This research aims to develop and evaluate the Lak Hok virtual tour navigation system to promote sustainable cultural tourism by showcasing Thai wisdom through immersive digital experiences. The system utilized 360-degree panoramic images hosted on a web server and supported accessibility via laptops, smartphones, and virtual reality (VR) headsets. Both subjective evaluations and objective performance metrics were employed to assess the system’s usability, aesthetic appeal, and content quality (CQ). User satisfaction, measured through a survey of 87 participants, demonstrated consistently high ratings (mean scores: 3.59-3.77 for ease of use (EU), 3.32-3.95 for design aesthetics, and 3.62-3.70 for content knowledge). Objective tests revealed an average system response time of 1.45 seconds, a false interaction rate of 4.2%, and a navigation accuracy of 98.5%. Statistical analysis showed no significant differences in user satisfaction across gender, age, or region, highlighting the system’s broad accessibility and usability. Unlike prior systems, this study formalizes satisfaction modeling via equation-based analysis. This virtual tour system provides a scalable and engaging platform for preserving and promoting cultural heritage, offering a sustainable solution for modern tourism development.
Volume: 41
Issue: 2
Page: 690-699
Publish at: 2026-02-01

Advancements in physical layer key generation: a review on channel reciprocity and IoT security techniques

10.12928/telkomnika.v24i1.27340
Syed Shafaq; Southeast University Ali Shah , Ajab; University of Science and Technology Bannu Noor , Ruiyue; Changchun University of Science and Technology Liang , Rahmat Ullah; FAST National University of Computer and Emerging Science Zadran
With the burgeoning internet of things (IoT), securing communication becomes paramount. Traditional cryptography does not meet computational needs and brute-force attacks. This review explores the state-of-the-art physical layer secret key generation (PLKG) that takes advantage of the inherent reciprocity and randomness of wireless channels. We investigate cutting-edge techniques such as feature extraction networks, domain adversarial training, and deep learning-based approaches, evaluating their effects on the security and efficiency of key generation. In addition to these methods, the review addresses real-world challenges such as multi-user scenarios, reconciliation overhead, and inconsistent channel measurement. We believe that improved key generation rates and security can be achieved through the use of millimeter wave technology and full-duplex communication. To strengthen the robustness of key generation, the paper concludes by suggesting future directions, such as incorporating more random sources, such as physiological signals and sensor data. This comprehensive overview offers deep insights into the state-of-the-art and paves the way for reliable communication in ever more complicated IoT settings.
Volume: 24
Issue: 1
Page: 196-205
Publish at: 2026-02-01

Information technology value engineering through partial adjustment valuation theory

10.12928/telkomnika.v24i1.27478
Lukman; Telkom University Abdurrahman , Candiwan; Telkom University Candiwan
The paper proposes a systems management approach that utilizes information technology (IT) treatment as a framework to help firms enhance future performance by optimising key parameters. The method certifies a valuation approach that enables businesses to better manage their IT infrastructure and improve performance. A case study of A case study of PT Telekomunikasi Indonesia (Telkom) and PT XL Axiata (XL) (2004–2018) shows the method’s effectiveness. Once the IT value is identified, specific parameters can be engineered to improve performance without changing other variables. The approach uses a partial adjustment valuation model, enabling performance gains at lower costs. The results show significant improvements in both firms’ performance values and ratios compared to their originals. This supports adopting a cost leadership strategy, making IT based businesses more efficient, cost-effective, and better performing across financial, business, and strategic dimensions.
Volume: 24
Issue: 1
Page: 111-125
Publish at: 2026-02-01

Machine learning models in the enhancement of PSE in high-dimensional socioeconomic data: a review

10.11591/ijeecs.v41.i2.pp645-654
Gene Marck B. Catedrilla , Joey Aviles
This study reviews the use of machine learning (ML) techniques to improve propensity score (PS) estimation in high-dimensional socioeconomic data. Traditional logistic regression (LR) often performs poorly under nonlinear and complex covariate structures, leading to bias and model misspecification. Across the reviewed studies, ensemble methods such as random forests (RF) and gradient boosting, and deep learning models consistently achieved better covariate balance, lower bias, and greater flexibility than conventional approaches, while classification-based methods improved performance in imbalanced datasets. The review also highlights practical considerations, including calibration, transparent reporting, and integration with doubly robust estimators to strengthen causal inference. The findings show that ML-based propensity score estimation (PSE) can substantially enhance the validity and reliability of socioeconomic evaluations, provided that its implementation is carefully guided by appropriate expertise and best-practice standards.
Volume: 41
Issue: 2
Page: 645-654
Publish at: 2026-02-01

Performance enhancement of embedded object detection via neural hardware acceleration

10.12928/telkomnika.v24i1.27448
Alwin; STMIK Indonesia Mandiri Hartono Limaran , Agung; STMIK Indonesia Mandiri Wicaksono , Patah; STMIK Indonesia Mandiri Herwanto
This paper presents the first benchmarking of you only look once version 11 (YOLO11) on the Rockchip RK3566 neural processing unit (NPU) within the Orange Pi 3B platform. Performance was compared between the quad-core ARM Cortex-A55 CPU and the integrated NPU using the COCO2017 dataset, evaluating latency, energy, and accuracy. NPU acceleration achieved >80% latency reduction and ≈ 94% lower per-inference energy consumption, with speedup of up to 16.7× while maintaining accuracy within 0.03 mean average precision (mAP) of the baseline. Average power remained nearly constant (3.60 W central processing unit (CPU) vs. 3.59 W NPU), indicating that the efficiency gains stem from reduced inference time rather than lower wattage. Limitations included unstable INT8 quantization due to unsupported operators and calibration-range mismatch, as well as minor CPU-side overhead in preprocessing and non-maximum suppression. The findings confirm that the RK3566 NPU delivers substantial efficiency gains without accuracy loss, enabling compact and low-cost platforms to sustain modern object-detection workloads. This demonstrates that affordable NPUs can provide reliable, real time artificial intelligence (AI) inference for embedded vision, internet of things (IoT), and robotics applications.
Volume: 24
Issue: 1
Page: 126-141
Publish at: 2026-02-01

An automatic stock price movement prediction using circularly dilated convolutions with orthogonal gated recurrent unit

10.11591/ijeecs.v41.i2.pp823-832
Durga Meena Rajendran , Maharajan Kalianandi , Bhuvanesh Ananthan
Recently, stock trend analysis has played an integral role in gaining knowledge about trading policy and determining stock intrinsic patterns. Several conventional studies reported stock trend prediction analysis but failed to obtain better performance due to poor generalization capability and high gradient vanishing problems. In light of the need to forecast stock price trends using both textual and empirical price data, this research proposed a novel hybridized deep learning (DL) model. Preprocessing, feature extraction, and prediction are the three effective stages that the created research goes through in order to properly estimate the stock movements. Data cleaning, which helps improve data quality, is calculated in the preprocessing step. Next, we use the created CDConv-OGRU technique-hybridized circularly dilated convolutions with orthogonal gated recurrent units-to extract features and make predictions. Python serves as the platform for processing and analyzing the created approach. This research uses a publicly accessible StockNet database for testing and compares results using a number of performance metrics, including accuracy, recall, precision, Mathew’s correlation coefficient (MCC), and f-score. In the experimental part, the created approach obtains a total of 95.16% accuracy, 94.8% precision, 94.89% recall, 95% confidence interval, and 0.9 MCC, in that order.
Volume: 41
Issue: 2
Page: 823-832
Publish at: 2026-02-01

Fraud detection using TabNet* classifier: a machine learning approach

10.11591/ijeecs.v41.i2.pp601-613
G. Anish Mary , S. Sudha
Detecting fraudulent transactions is a big challenge in the digital financial world. Transaction volumes are growing quickly, and new attack methods often outstrip traditional detection systems. Current fraud-detection models usually lack clarity and do not perform reliably on unbalanced real-world datasets. This highlights the urgent need for clear and explainable deep-learning methods for tabular financial data. This paper presents an interpretable deep learning framework built on the TabNet classifier. It uses attention-driven feature selection, sparse representation learning, and sequential decision reasoning to model complex interactions among transactional, demographic, and geographical factors. The model was tested on a real-world credit card transaction dataset with 23 features. It achieved 99.69% accuracy, a 0.975 F1-score, and a 0.956 ROC-AUC. This performance outperforms benchmark models such as random forest, XGBoost, LightGBM, and logistic regression. In addition to outstanding predictive results. Furthermore, interpretability is enhanced by TabNet's attention-based feature attribution. This facilitates the clear understanding of model decisions, supporting its use in regulated financial environments where precision and responsibility are crucial.
Volume: 41
Issue: 2
Page: 601-613
Publish at: 2026-02-01

RAC: a reusable adaptive convolution for CNN layer

10.11591/ijeecs.v41.i2.pp753-763
Nguyen Viet Hung , Phi Dinh Huynh , Pham Hong Thinh , Phuc Hau Nguyen , Trong-Minh Hoang
This paper proposes reusable adaptive convolution (RAC), an efficient alternative to standard 3×3 convolutions for convolutional neural networks (CNNs). The main advantage of RAC lies in its simplicity and parameter efficiency, achieved by sharing horizontal and vertical 1×k/k×1 filter banks across blocks within a stage and recombining them through a lightweight 1×1 mixing layer. By operating at the operator design level, RAC avoids post-training compression steps and preserves the conventional Conv–BN–activation structure, enabling seamless integration into existing CNN backbones. To evaluate the effectiveness of the proposed method, extensive experiments are conducted on CIFAR-10 using several architectures, including ResNet-18/50/101, DenseNet, WideResNet, and EfficientNet. Experimental results demonstrate that RAC significantly reduces parameters and memory usage while maintaining competitive accuracy. These results indicate that RAC offers a reasonable balance between accuracy and compression, and is suitable for deploying CNN networks on resource-constrained platforms.
Volume: 41
Issue: 2
Page: 753-763
Publish at: 2026-02-01

Hybrid SVM–ANN system for automated MRI diagnosis of anterior cruciate ligament injuries

10.11591/ijeecs.v41.i2.pp773-781
Sazwan Syafiq Mazlan , Azizi Miskon , Sharizal Ahmad Sobri
Anterior cruciate ligament (ACL) tears are a frequent cause of knee instability, yet magnetic resonance imaging (MRI) interpretation remains time-consuming and observer-dependent. This paper presents an automated MRI framework for ACL injury screening and severity grading using a hybrid support vector machine–artificial neural network (SVM–ANN) model. A balanced dataset of 600 sagittal knee MRI images from Hospital Taiping (normal, partial tear, complete tear) was standardized via resizing, region-of-interest cropping, contrast enhancement, noise filtering, and segmentation. Morphological and texture features were extracted and reduced using principal component analysis (PCA). The SVM performs the initial screening (injured vs. non-injured) and samples predicted as injured are passed to the artificial neural network (ANN) to classify severity. Using confusion-matrix and receiver operating characteristic (ROC) evaluation, the proposed system achieved 86.2% overall accuracy and 81.7% sensitivity, with the ANN reaching approximately 95% accuracy on injured cases forwarded for grading. A clinician usability survey indicated high acceptance (~95%), supporting the feasibility of deployment as a lightweight decision-support tool. Limitations include reliance on single sagittal slices and single-sequence data; future work will incorporate multi-slice/3D and multi-sequence MRI to improve sensitivity and generalizability.
Volume: 41
Issue: 2
Page: 773-781
Publish at: 2026-02-01

Anchovy-inspired filter algorithm: A bio-inspired optimization approach for high-dimensional benchmark functions

10.12928/telkomnika.v24i1.27594
Azrul; Politeknik Sultan Idris Shah Mahfurdz , Muhammad Muizz; Politeknik Sultan Idris Shah Mohd Nawawi , Sunardi; Universitas Ahmad Dahlan Sunardi , Mohd Azriq; Sapura Industrial Berhad, Bandar Baru Bangi Abd Aziz
This paper presents the anchovy-inspired filter algorithm (AFA), a novel bio-inspired metaheuristic optimization method motivated by the filter feeding behavior of anchovies. Unlike conventional swarm intelligence algorithms, AFA employs a filtering mechanism in which each agent generates multiple candidate solutions within a local sampling radius and selects the best, mimicking how anchovies filter microscopic prey from seawater. To evaluate its performance, AFA was benchmarked against particle swarm optimization (PSO) and genetic algorithm (GA) using six standard test functions: Sphere, Rosenbrock, Schwefel 1.2, Rastrigin, Griewank, and Ackley in 30-dimensional search spaces. Simulation results demonstrate that AFA consistently outperforms PSO and GA across unimodal and multimodal functions. For unimodal problems such as Sphere, Rosenbrock, and Schwefel 1.2, AFA achieved significantly lower best and mean fitness values, reflecting strong exploitation capability. For multimodal functions including Rastrigin, Griewank, and Ackley, AFA effectively avoided local minima, maintained robustness, and achieved stable convergence with lower variance. Convergence analysis further indicates that AFA steadily approaches near-global optima without premature stagnation. Overall, the results highlight the effectiveness of the filter-based exploitation mechanism in balancing exploration and exploitation. Future research will focus on adaptive filtering strategies, hybrid integration with other metaheuristics, and applications to real-world optimization problems.
Volume: 24
Issue: 1
Page: 271-281
Publish at: 2026-02-01

IoT-enabled connected incubator with redundant communication for real-time neonatal monitoring

10.11591/ijeecs.v41.i2.pp633-644
Naçima Mellal , Soumia Hadj Maatallah , Ammar Merazga , Rachida Bouchouareb , Souad Nacer
Premature birth remains a major challenge in neonatal care, especially in resource-constrained settings, where continuous monitoring and timely intervention are limited. Most existing neonatal incubators offer limited real-time monitoring, unreliable alerting, and lack communication redundancy, potentially delaying critical responses. This paper presents a comprehensive internet of thing (IoT) enabled connected incubator with redundant communication (Wi-Fi and GSM) for real-time monitoring of physiological and environmental parameters. The system integrates sensing, processing, cloud connectivity, a mobile application, and multi-channel alerts (App notifications, SMS, voice calls, and local alarms). It was experimentally evaluated under controlled laboratory conditions. Quantitative evaluation shows a cloud transmission success rate of 99.1%, end-to-end communication latency below 1 second via Wi-Fi and 2.2 seconds via GSM, with 98% of alerts successfully delivered within 6 seconds. The proposed system provides a low-cost, reliable platform that enhances neonatal safety, supports timely clinical decisions, and is scalable for resource-constrained healthcare environments.
Volume: 41
Issue: 2
Page: 633-644
Publish at: 2026-02-01

Newchaos function from the composition of DTM and Gauss iterated map for digital image encryption

10.12928/telkomnika.v24i1.27551
Adrianus; Universitas Indonesia Yosia , Tokonyai Tawanda Jonathan; Universitas Indonesia Rabvemhiri , Suryadi; Universitas Indonesia MT
This manuscript introduces a novel chaotic discrete function, formulated through the composition of the dyadic transformation map (DTM) and the Gauss iterated map (GIM), and designated as DTGIM. The National Institute of Science and Technology (NIST) randomness test suite, bifurcation diagrams, and Lyapunov exponents are used to examine the chaotic characteristics of DTGIM. With ini tial condition x0 = 0.12345 and parameters α = −15 and β = 0.3, the func tion shows chaotic behavior in the bifurcation diagram and produces a positive Lyapunov exponent. Strong randomness is further confirmed by NIST tests, which achieve 100% for 32-bit binary sequences and 63.75% for 8-bit binary sequences. Additionally, we compare a number other chaotic discrete functions that also employ the composition method. These findings show that DTGIM is a viable option for applications involving chaos-based cryptography.
Volume: 24
Issue: 1
Page: 228-239
Publish at: 2026-02-01

Stable and accurate customer churn prediction: comparative analysis of eight classification algorithms

10.11591/ijeecs.v41.i2.pp655-665
Vincent Alexander Haris , Muhammad Ilyas Arsyad , Nathanael Septhian Adi Nugraha , Yasi Dani , Maria Artanta Ginting
Predicting customer churn is a challenging problem in many subscription-based industries, though it is considered more cost-effective than acquiring new customers. In this research, customer churn is predicted using a public dataset from an internet service provider, with 72,274 instances and 55% churn rate. The main contribution is to provide a comprehensive comparison of the stability and performance of eight classification algorithms in customer churn prediction using a large-scale public dataset. The research process includes data collection, data preprocessing, feature engineering, and model evaluation. The metrics evaluation presents test accuracy, accuracy gap, precision, recall, F1-Score, and ROC AUC, with stratified K-Fold cross-validation. Since the proportion of churn and non-churn in the dataset is relatively balanced, the F1-score is considered as the primary evaluation metric, as it provides a balanced assessment of precision and recall for both classes. The results show that CatBoost and XGBoost are the most effective models that achieve high F1-scores of 94.97% and 94.92%, respectively.
Volume: 41
Issue: 2
Page: 655-665
Publish at: 2026-02-01

Predicting non-performing loans in Vietnam’s financial sector: a deep Q-learning approach

10.11591/ijeecs.v41.i2.pp700-709
Luyen Anh Do , Huong Thi Viet Pham , Thinh Duc Le , Oanh Thi Tran
Non-performing loans (NPLs) prediction is a very important task in risk management of financial institutions. NPLs often lead to substantial losses when loans are not paid back on time. While traditional machine learning (ML) models have been conventionally exploited for credit risk assessment, they frequently face challenges with handling imbalanced data. To deal with this problem, this paper introduces a novel approach using deep reinforcement learning (DRL), specifically deep Q-learning, to enhance the prediction of NPLs. To verify the effectiveness of the method, we introduce a new dataset comprising 83,732 customer records (each described with 22 key features) from one of Vietnam's largest financial entities. Our method is compared with standard ML techniques such as random forest, decision tree, logistic regression, support vector machine, LightGBM, and XGBoost. Experimental results on this dataset demonstrate that deep Q-learning outperforms these traditional models in handling imbalanced data and boosting prediction accuracy. This research highlights the potential of DRL as a robust risk management tool, helping financial institutions make credit assessments more efficiently and reducing decision-making costs.
Volume: 41
Issue: 2
Page: 700-709
Publish at: 2026-02-01

Deep learning-based power amplifier linearization in OFDM systems with unknown channel state information

10.12928/telkomnika.v24i1.27236
Meryem Mamia; University of Tlemcen Benosman , Mohammed Yassine; University of Tlemcen Bendimerad , Fethi Tarik; University of Tlemcen Bendimerad
This paper presents an end-to-end deep learning-based approach for orthogonal frequency-division multiplexing (OFDM) communication systems impaired by nonlinear power amplifiers (PAs) and channel fading. The PA nonlinearity is modeled using the modified Rapp model, and simulations are performed on a 64-subcarrier OFDM system with a cyclic prefix (CP) of 8 and 16-quadrature amplitude modulation (16-QAM). The proposed autoencoder-based OFDM–PA (AE-OFDM-PA) system jointly optimizes the transmitter and receiver through end-to-end learning, enabling simultaneous compensation of both PA nonlinearities and channel distortions without requiring explicit channel state information (CSI) estimation. Instead, the model leverages embedded pilot sequences to learn the implicit CSI representation directly from data, allowing the receiver to correct amplitude and phase distortions adaptively. Simulation results demonstrate that AE-OFDM-PA significantly outperforms conventional OFDM and OFDM-PA systems, achieving over 70× block error rate (BLER) improvement compared with the uncompensated OFDM-PA system at an input back-off (IBO) of 3 dB. Furthermore, the proposed method achieves approximately 11.5 dB adjacent channel leakage ratio (ACLR) improvement over the classical memory polynomial digital predistortion (DPD) technique, while slightly reducing the peak-to-average power ratio (PAPR). Overall, AE-OFDM-PA provides a robust, spectrally efficient, and low-complexity solution for nonlinear and fading environments with unknown or varying CSI.
Volume: 24
Issue: 1
Page: 1-13
Publish at: 2026-02-01
1 2 3
...
2025 2026
Show 79 of 2026

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