cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Nizirwan Anwar
Contact Email
nizirwan.anwar@esaunggul.ac.id
Phone
-
Journal Mail Official
telkomnika@ee.uad.ac.id
Editorial Address
Ahmad Yani st. (Southern Ring Road), Tamanan, Banguntapan, Bantul, Yogyakarta 55191, Indonesia
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
TELKOMNIKA (Telecommunication Computing Electronics and Control)
Published by Universitas Ahmad Dahlan
ISSN : 16936930     EISSN : 23029293     DOI : 10.12928
Core Subject : Science,
Computer Science & IT
Submitted papers are evaluated by anonymous referees by single blind peer review for contribution, originality, relevance, and presentation. The Editor shall inform you of the results of the review as soon as possible, hopefully in 10 weeks. Please notice that because of the great number of submissions that TELKOMNIKA has received during the last few months the duration of the review process can be up to 14 weeks. Communication Engineering, Computer Network and System Engineering, Computer Science and Information System, Machine Learning, AI and Soft Computing, Signal, Image and Video Processing, Electronics Engineering, Electrical Power Engineering, Power Electronics and Drives, Instrumentation and Control Engineering, Internet of Things (IoT)
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 3,452 Documents
 317   318   319   320   321 
Hybrid classical–quantum ensemble learning for real-time flight delay prediction at Tribhuvan International Airport Pavan Khanal; Nanda Bikram Adhikari
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 24, No 2: April 2026
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v24i2.27240

Abstract

This study investigates ensemble learning using classical and quantum-inspired models to predict flight delays at Tribhuvan International Airport (TIA), Nepal. It combines traditional machine learning algorithms with quantum-based approaches, quantum boosting (QBoost) and the hybrid QBoostPlus, leveraging quantum properties for faster computation. The dataset includes flight records from 2020 to 2024 and Meteorological Aerodrome Reports (METAR), analyzed across four sea- sons to capture delay patterns in domestic and international flights. A combined seasonal dataset assesses model generalization. Six models; VotingClassifier, adaptive boosting (AdaBoost), xtreme gradient boosting (XGBoost), categorical boosting (CatBoost), QBoost, and QBoostPlus are evaluated based on accuracy, precision, recall, F1 score, area under the curve(AUC), and execution time. CatBoost achieved high accuracy (up to 0.97) but slower execution (up to 10,570.63 ms). QBoostPlus provides competitive AUC scores (0.83–0.95) with faster execution, improving speed by up to 99.94% and generating predictions in as little as 6.46 ms. Although quantum-inspired models have slightly lower accuracy, their computational efficiency and stability show strong potential for real-time flight delay prediction. This is the first study applying quantum-inspired ensemble learning to Nepalese aviation data, showing promise for regional airports with limited infrastructure.
Enhancing object detection for humanoid robot soccer: comparative analysis of three models Handaru Jati; Nur Alif Ilyasa; Yuniar Indrihapsari; Ariadhie Chandra; Dhanapal Durai Dominic
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 4: August 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i4.25906

Abstract

The humanoid robot soccer system encounters a notable challenge in object detection, primarily concentrating on identifying the ball and often neglecting crucial elements like opposing robots and goals, resulting in on-field collisions and imprecise ball shooting. This study comparatively evaluates three you only look once (YOLO) real-time object detection system variants: YOLOv8, YOLOv7, and YOLO-NAS. A dataset of 2104 annotated images, covering classes such as ball, goalpost, and robot, was curated from Roboflow and robot-captured images. The dataset was partitioned into training, validation, and testing sets, and each YOLO model underwent extensive fine-tuning over 100 epochs on this custom dataset, leveraging the pre-trained common objects in context (COCO) model. Evaluation metrics, including mean average precision (mAP) and inference speed, assessed performance. YOLOv8 achieved the highest accuracy with a mAP of 0.92, while YOLOv7 showed the fastest inference speed of 24 ms on the Jetson Nano platform. Balancing accuracy and speed, YOLO-NAS emerged as the optimal choice. Thus, YOLO-NAS is recommended for object detection for humanoid soccer robots, regardless of team affiliation. Future research should focus on enhancing object detection through advanced training techniques, model architectures, and sensor fusion for improved performance in dynamic environments, potentially optimizing through scenario-specific fine-tuning.
Appropriateness of EToU electricity tariff program for industrial type consumers: an investigation of cost benefit Mohamad Fani Sulaima; Farah Anishah Zaini; Amira Noor Farhanie Ali; Intan Azmira Wan Abdul Razak; Elia Erwani Hassan; Nur Elida Mohamad Zahari
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 21, No 1: February 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v21i1.24260

Abstract

In mitigating the peak demand, the energy authority in Malaysia has introduced the enhanced time of use (EToU). However, the number of participants joining the programs is less than expected. Due to that reason, this study investigated the investment benefit in terms of electricity cost reduction when consumers subscribe to the EToU tariff scheme. The significant consumers from industrial tariff types have been focused on where the load profiles were collected from the incoming providers’ power stations. Meanwhile, ant colony optimization (ACO) and particle swarm optimization (PSO) are applied to optimize the load profiles reflecting EToU tariff prices. The proposed method had shown a reduction in electricity cost, and the most significant performance has been recorded congruently. For a maximum 30% load adjustment using ACO optimization, the electricity costs have been decreased by 10% (D type of tariff), 16% (E1 type of tariff), 9% (E2 kind of tariff), and 1.13% (E3 type of tariff) when compared to the existing conventional tariff. The cost-benefit of the EToU tariff switching has been identified where the simple payback period (SPP) is below one year for all the industrial types of consumers.
Addressing overfitting in comparative study for deep learning-based classification Jing-Yee Ong; Lee-Yeng Ong; Meng-Chew Leow
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 23, No 3: June 2025
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v23i3.26451

Abstract

Despite significant advancements in deep learning methodologies for animal species classification, there remains a notable research gap in effectively addressing biases inherent in training datasets, combating overfitting during model training, and enhancing overall performance to ensure reliable and accurate classification results in real-world applications. Therefore, this study explores the complex challenges of dog species classification, with a specific focus on addressing biases, combatting overfitting, and enhancing overall performance using deep learning methodologies. Initially, the Stanford Dog dataset serves as the foundation for training, complemented by additional data from annotated datasets. The primary aim is to mitigate biases and reduce overfitting, which is essential for improving the performance of deep learning-based classification in terms of dataset size and computational time. Feature extraction and few-shot learning techniques are compared to assess and improve the model performance. The experimentation involves the utilization of optimal classifiers, specifically InceptionV3 and Xception. In order to tackle overfitting, a range of strategies are deployed, including data augmentation, early stopping, and the integration of dropout and freezing layers which particularly achieved a better performance with Xception on the augmented dataset.
Qualitative assessment of image enhancement algorithms for mammograms based on minimum EDV Mazin N. Farhan; Mohammed G. Ayoub; Hassan M. Qassim; Abdulrahman K. Eesee
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 2: April 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i2.14085

Abstract

Breast cancer is one of the leading reason of death among women. Nevertheless, medications for this fatal disease are still away of ambitions. Patients (thought to have breast cancer) should go through several advanced medical diagnostic procedures like mammography, biopsy analysis, ultrasound imaging, etc. Mammography is one of the medical imaging techniques used for detecting breast cancer. However, its resulted images may not be clear enough or helpful for physician to diagnose each case correctly. This fact has pushed researchers towards developing effective ways to enhance images throughout using various enhancement algorithms. In this paper, a comparison amongst these applied algorithms was done to evaluate the optimum enhancement technique. A morphology enhancement, which is resulted from combining top-hat operation and bottom-hat operation, was used as a proposed enhancement algorithm. The proposed enhancement algorithm was compared to three other well-known enhancement algorithms, specifically histogram equalization, logarithmic transform, and gamma correction with different gamma values. Twenty-five mammographic images were taken from the mammography image analysis society (MIAS) database samples. The minimum entropy difference value (EDV) was used as metric to evaluate the best enhancement algorithm. Results has approved that the proposed enhancement algorithm gave the best-enhanced images in comparison to the aforementioned algorithms.
Investigation of classical segmentation's impact on paddy disease classification performance Hemanthakumar R. Kappali; Sadyojatha KalapurMath
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 21, No 6: December 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v21i6.25505

Abstract

The key source of information for disease diagnosis and classification in paddy diseases is the leaves. Applying hybrid techniques, such as image processing-pattern recognition (IP-PR) and computer vision-based technologies, is the answer to assessing the health of plants. The following paddy diseases are considered in this paper: bacterial leaf blight (BLB), brown spot (BS), leaf smut (LS), and narrow brown spot (NBS) from the machine learning repository. A classical colour threshold-based segmentation method is implemented newly to separate the patterns of image pixels into the diseased part and the normal part. The human visual impression (VI), a subjective method, and a parametric-based method with an average error rate (ER) and overlap rate (OR) are used to assess the uniqueness of the suggested segmentation technique. Using a multi-class support vector machine (MSVM) classifier, the analysis yielded segmented images using the proposed method with an accuracy of 92% over the existing method with an accuracy of 76.60%. The BLB disease achieved the highest identification accuracy of 91%. Our proposed method evaluates the segmentation performance and achieved consistent accuracy higher than the previous segmentation work.
Dorsal hand veins features extraction and recognition by correlation coefficient Maha A. Rajab; Kadhim M. Hashim
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 20, No 4: August 2022
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v20i4.22068

Abstract

One of the most convenient biometrics approaches for identifying a person is dorsal hand veins recognition. In recent years, the dorsal hand veins have acquired increasing attention because of its characteristics such as universal, unique, permanent, contactless, and difficulty of forging, also, the veins remain unchanged when a human being grows. The captured dorsal hand veins image suffers from the many differences in lighting conditions, brightness, existing hair, and amount of noise. To solve these problems, this paper aims to extract and recognize dorsal hand veins based on the largest correlation coefficient. The proposed system consists of three stages: 1) preprocessing the image, 2) feature extraction, and 3) matching. In order to evaluate the proposed system performance, two databases have been employed. The test results illustrate the correct recognition rate (CRR), and accuracy of the first database are 99.38% and 99.46%, respectively, whereas the CRR, and accuracy of the second database are 99.11% and 99.07% respectively. As a result, we conclude that our proposed method for recognizing dorsal hand veins is feasible and effective.
Hybrid GA–SA optimization for eMBB-oriented spectrum allocation in 5G device-to-device communication Mohd Azrulazwan Jusoh @ Mohd Yusoff; Nor Fadzilah Abdullah; Asma’ Abu Samah
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 24, No 3: June 2026
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v24i3.27394

Abstract

The explosive growth of enhanced mobile broadband (eMBB) services in fifth generation (5G) networks presents new challenges in maintaining quality of service (QoS), particularly under dense deployments with device-to-device (D2D) communication. Interference caused by spectrum reuse among D2D pairs and cellular users can significantly degrade signal-to-interference-plus-noise ratio or signal-to-interference-plus-noise ratio (SINR), throughput, and fairness. This paper addresses the underexplored problem of optimizing spectrum allocation in eMBB-specific D2D scenarios by proposing a hybrid metaheuristic framework combining genetic algorithm (GA) and simulated annealing (SA). The proposed hybrid GA–SA algorithm leverages GA’s global exploration and SA’s local exploitation to improve allocation quality while ensuring robustness. Simulation results reveal that the hybrid approach achieves up to 25% improvement in SINR, an 18% increase in aggregate throughput, and a 22% reduction in interference compared to standalone GA and SA algorithms. Furthermore, the framework achieves improved fairness performance while maintaining competitive SINR and throughput under dense eMBB-oriented deployment scenarios. The algorithm demonstrates efficient convergence behavior and scalability to larger user populations, making it suitable for real-time or large-scale deployments. These results affirm the significance of tailored hybrid optimization in interference-aware spectrum management for future 5G networks.
3D word embedding vector feature extraction and hybrid CNN-LSTM for natural disaster reports identification Mohammad Reza Faisal; Dodon Turianto Nugrahadi; Irwan Budiman; Muliadi Muliadi; Mera Kartika Delimayanti; Septyan Eka Prastya; Imam Tahyudin
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 5: October 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i5.26091

Abstract

Social media contain various information, such as natural disaster reports. Artificial intelligence is used to identify reports from eyewitnesses early for disaster warning systems. The artificial intelligence system includes a text classification model with feature extraction and classification algorithms. Word embedding-based feature extraction is widely used for 1-dimensional (1D) and 2-dimensional (2D) data, suitable for traditional or deep learning algorithms. However, applying feature extraction to 3-dimensional (3D) data for text classification is limited. Previous studies focused on word embedding for 1D, 2D, and 3D outputs with convolutional neural network (CNN). Yet, using 3D data and CNN did not perform well. Despite using CNN and 3D variants, identifying natural disaster reports remains below 80% accuracy. This research aims to improve identifying earthquakes, floods, and forest fires with 3D data and hybrid CNN long short-term memory (LSTM). The study found models with accuracies of 83.38%, 83.72%, and 89.03% for each disaster type. Hybrid CNN LSTM significantly enhanced identification compared to CNN alone, supported by statistical tests with P value less than 0.0001.
Decoding of the extended Golay code by the simplified successive-cancellation list decoder adapted to multi-kernel polar codes Driss Khebbou; Idriss Chana; Hussain Ben-Azza
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 21, No 3: June 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v21i3.23360

Abstract

This paper describes an adaptation of a polar code decoding technique in favor of the extended Golay code. Based on the bridge provided by a permutation matrix between the code words of these two classes of codes, the Golay code can be decoded by any polar code technique. Contrary to the successive-cancellation list technique which is characterized by a serial estimation of the bits, we propose in this work an adaptation of the simplified successive-cancellation list technique to polar codes equivalent to the Golay code. The simulations have achieved the performance of a maximum likelihood decoding, with the low decoding complexity of polar codes, compared to one of the universal decoders of linear codes most known in the literature.

Page 319 of 346 | Total Record : 3452

 317   318   319   320   321 

Filter by Year

2004 2026


Reset
Filter By Issues
All Issue Vol 24, No 4: August 2026 Vol 24, No 3: June 2026 Vol 24, No 2: April 2026 Vol 24, No 1: February 2026 Vol 23, No 6: December 2025 Vol 23, No 5: October 2025 Vol 23, No 4: August 2025 Vol 23, No 3: June 2025 Vol 23, No 2: April 2025 Vol 23, No 1: February 2025 Vol 22, No 6: December 2024 Vol 22, No 5: October 2024 Vol 22, No 4: August 2024 Vol 22, No 3: June 2024 Vol 22, No 2: April 2024 Vol 22, No 1: February 2024 Vol 21, No 6: December 2023 Vol 21, No 5: October 2023 Vol 21, No 4: August 2023 Vol 21, No 3: June 2023 Vol 21, No 2: April 2023 Vol 21, No 1: February 2023 Vol 20, No 6: December 2022 Vol 20, No 5: October 2022 Vol 20, No 4: August 2022 Vol 20, No 3: June 2022 Vol 20, No 2: April 2022 Vol 20, No 1: February 2022 Vol 19, No 6: December 2021 Vol 19, No 5: October 2021 Vol 19, No 4: August 2021 Vol 19, No 3: June 2021 Vol 19, No 2: April 2021 Vol 19, No 1: February 2021 Vol 18, No 6: December 2020 Vol 18, No 5: October 2020 Vol 18, No 4: August 2020 Vol 18, No 3: June 2020 Vol 18, No 2: April 2020 Vol 18, No 1: February 2020 Vol 17, No 6: December 2019 Vol 17, No 5: October 2019 Vol 17, No 4: August 2019 Vol 17, No 3: June 2019 Vol 17, No 2: April 2019 Vol 17, No 1: February 2019 Vol 16, No 6: December 2018 Vol 16, No 5: October 2018 Vol 16, No 4: August 2018 Vol 16, No 3: June 2018 Vol 16, No 2: April 2018 Vol 16, No 1: February 2018 Vol 15, No 4: December 2017 Vol 15, No 3: September 2017 Vol 15, No 2: June 2017 Vol 15, No 1: March 2017 Vol 14, No 4: December 2016 Vol 14, No 3: September 2016 Vol 14, No 2: June 2016 Vol 14, No 1: March 2016 Vol 13, No 4: December 2015 Vol 13, No 3: September 2015 Vol 13, No 2: June 2015 Vol 13, No 1: March 2015 Vol 12, No 4: December 2014 Vol 12, No 3: September 2014 Vol 12, No 2: June 2014 Vol 12, No 1: March 2014 Vol 11, No 4: December 2013 Vol 11, No 3: September 2013 Vol 11, No 2: June 2013 Vol 11, No 1: March 2013 Vol 10, No 4: December 2012 Vol 10, No 3: September 2012 Vol 10, No 2: June 2012 Vol 10, No 1: March 2012 Vol 9, No 3: December 2011 Vol 9, No 2: August 2011 Vol 9, No 1: April 2011 Vol 8, No 3: December 2010 Vol 8, No 2: August 2010 Vol 8, No 1: April 2010 Vol 7, No 3: December 2009 Vol 7, No 2: August 2009 Vol 7, No 1: April 2009 Vol 6, No 3: December 2008 Vol 6, No 2: August 2008 Vol 6, No 1: April 2008 Vol 5, No 3: December 2007 Vol 5, No 2: August 2007 Vol 5, No 1: April 2007 Vol 4, No 3: December 2006 Vol 4, No 2: August 2006 Vol 4, No 1: April 2006 Vol 3, No 3: December 2005 Vol 3, No 2: August 2005 Vol 3, No 1: April 2005 Vol 2, No 1: April 2004 More Issue