TELKOMNIKA (Telecommunication Computing Electronics and Control)
Not a member yet
3120 research outputs found
Sort by
Design and implementation of a power supply unit for a smart airport lighting control system
Full text linkIn this paper, a buck-boost converter is used to design and implement a power supply for intelligent airport lighting system applications. Innovative approaches to power supply design are required to meet the increasing demand for fault detection solutions for lighting systems in vital infrastructure such as airports. The buck-boost converter’s ability to step up or down input voltage levels makes it particularly well suited to this application, ensuring stable operation over a range of load conditions. With a fast-settling time of 26 ms at 6.1 V input and dropping to 6 ms at 22.4 V input, the power supply offers exceptional output stability. The output stabilizes steadily at 5 V with low ripple over a wide input voltage range (5 V to 23 V). The physical prototype, simulations, component selection and circuit design are all carefully tested and supported by experimental results. According to these results, the proposed converter-based power unit operates with stability and reliability, making it ideal for demanding lighting applications. By improving power stability in dynamic environments, this work improves the reliability of aviation infrastructure power systems and lays the groundwork for future advances in intelligent airport technologies
Advanced pneumonia classification using transfer learning on chest X-ray data with EfficientNet and ResNet
Full text linkPneumonia is a serious lung infection that demands accurate and timely diagnosis to reduce mortality. This study explores the use of deep learning and transfer learning for classifying chest X-ray images into two categories: normal and pneumonia. A total of 5,632 labeled images were used to train and evaluate six pre-trained convolutional neural network (CNN) architectures: EfficientNetB1, B3, B5, B7, ResNet50, and ResNet101. The models were tested across three training scenarios by varying learning rates (LR), batch sizes, and epochs. Among all models, EfficientNetB3 achieved the highest performance, with accuracy of 99.04%, precision of 99.76%, recall of 99.23%, and F1-score of 99.34%. These results indicate that EfficientNetB3 offers a robust and efficient solution for pneumonia detection. This research contributes to the development of intelligent diagnostic tools in the medical field and provides practical guidance for selecting effective deep learning models in clinical imaging applications
Optimizing vehicle inspection efficiency and integrity in Tanzania through blockchain technology
Full text linkThis study proposes a blockchain-based solution to improve the efficiency and integrity of vehicle inspections in Tanzania, with a focus on the National Institute of Transport. The system combines Hyperledger fabric, a permissioned blockchain that provides identity management and fine-grained access control, with the InterPlanetary file system (IPFS), a decentralized content-addressed store for large artifacts such as inspection images and portable document format (PDF) forms. Smart contracts encode inspection rules and approvals, which yield tamper-evident records, faster retrieval of histories, and uniform enforcement across centers. A mathematical model based on the M/M/1 queueing system, combined with a cost-benefit analysis, supports empirical findings: the total inspection cycle time decreases by approximately 30 percent, the average waiting time declines by about 20 to 30 percent, and annual operational savings reach approximately USD 800,000. These gains enhance auditability and transparency, which contribute to road safety outcomes by reducing opportunities for tampering and error. The design includes offline capture with later synchronization, which suits centers with intermittent connectivity. The approach is transferable to adjacent public services, for example, licensing, fine collection, and selected registries
Watermarking on spread multi-frame data video using discrete wavelet transform hybrid and frame ratio message variance
Full text linkThe exponential growth of video sharing demands secure and imperceptible watermarking methods. This study presents a video watermarking framework using discrete wavelet transform (DWT) with hybrid sub-band embedding and multi-frame allocation to balance imperceptibility, capacity, and robustness. Watermark bits are adaptively distributed across low-low (LL), low-high (LH), and high-low (HL) sub-bands of selected frames, with uncompressed audio video interleave (AVI) ensuring coefficient integrity. Experiments on 640×360 videos show LL-only embedding achieves high imperceptibility (peak signal-to-noise ratio (PSNR) > 38.6 dB, structural similarity index measure (SSIM) ≥ 0.9945, and bit error rate (BER) = 0), while LL-dominant hybrids increase capacity with slight robustness trade-offs. Embedding in LH and high-high (HH) sub-bands raises distortion vulnerability. Under cropping, BER rises from 0.005 to 0.205 (0–50%), and normalized correlation (NC) drops from 0.998 to 0.802, remaining acceptable for ≤30% cropping. The scheme resists joint photographic experts’ group (JPEG) compression quality factor 20–80 (Q20–Q80), resizing (≥70%), and mild Gaussian blur (3×3), maintaining efficient decoding under higher payloads. Future work may apply error-correction coding and redundancy-aware embedding for improved resilience. Overall, the proposed method offers a secure, adaptive, and efficient solution for video authentication and covert communication
The effectiveness of bentonite in reducing soil resistance in acidic water swampland
Full text linkThis study aims to evaluate the effectiveness of bentonite mixtures in reducing grounding resistance in acidic swampy areas. The method used is an experiment comparing resistance before and after the addition of bentonite in various compositions (25%, 50%, 75%, and 100%), supplemented with linear regression analysis. The results showed that bentonite significantly reduced soil resistance in three types of electrodes: iron rebar, copper-coated iron, and galvanised iron. The highest reduction in resistance was achieved in iron rebar electrodes, from 35.93 Ω to 22.46 Ω (a 37% reduction) with the addition of 25% bentonite. Linear regression analysis showed a consistent negative relationship between the percentage of bentonite and grounding resistance, with a coefficient of determination (R²) varying between 26.40% and 73.39%. These findings indicate that bentonite is effective as a natural grounding material in acidic swampy areas. This research makes an important contribution to the development of more efficient and safer electrical systems in swampy areas and challenging environments, while also supporting the use of natural materials to reduce dependence on synthetic chemicals
Object detection and tracking with decoupled DeepSORT based on αβ filter
Full text linkWith the rapid growth of the population, the demand for autonomous video surveillance systems has substantially increased. Recently, artificial intelligence has played a key role in the development of these systems. In this paper, we present an enhanced autonomous system for object detection and tracking in video streams, tailored for transportation and video surveillance applications. The system comprises two main stages: detection stage; this stage employs you only look once (YOLO)v8m, trained on the KITTI dataset, and is configured to detect only pedestrians and cars. The model achieves an average precision of 97.3% and 87.1% for cars and pedestrians classes respectively, resulting a final mean average precision (mAP) of 92.2%. Tracking stage; the tracking component utilizes the DeepSORT algorithm, which originally incorporates a Kalman filter for motion prediction and performs data association using cosine and Mahalanobis distances to maintain consistent object identifiers across frames. To improve tracking performance, we introduce two key modifications to the original DeepSORT: architecture modification and Kalman filter replacement. The tracking tests are carried out on KITTI and MOTChallenge Benchmarks. The final order tracking accuracy (HOTA) scores achieve 77.645 and 54.019 for Cars and Pedestrians classes respectively in the KITTI-Benchmark and 45.436 for the Pedestrians class in the MOTChallenge-Benchmark
Leveraging technology to improve tuberculosis patient adherence: a comprehensive review
Full text linkTuberculosis (TB) is a chronic disease that requires long-term treatment, generally for at least 6 to 9 months. Patients should follow the recommended treatment scheme regularly and completely. Poor adherence to treatment can cause patients to remain a source of infection for others. Patients with TB need additional support during treatment, in terms of information, motivation, and emotional support. Compliance monitoring helps ensure that patients take drugs according to a predetermined schedule. Comprehensive approach review method, careful selection of relevant data from various sources. This aims to provide overview of modern technology used to optimize the success of TB treatment. This paper aims to provide various methods that have existed in conventional and technology-enhanced approaches to monitoring and evaluating the treatment of TB patients. The existing studies only focus on making tools as a reminder to take medication but do not evaluate whether the drug is consumed. In addition, this paper describes prospective ideas involving advanced technology by using the internet of things (IoT)-based smart medicine bottle to accommodate the problem and become an effective communication solution in TB medication
Energy-efficient certificateless signcryption for secure data transfer in wireless sensor networks
Full text linkWireless sensor networks (WSN) have gained high popularity in the realm of technological innovation and have a prime responsibility of transferring the data safely to the sink despite the vulnerable situation presiding around the network. There needs to be a compromise made between energy consumption and the intricate network security system because they are inversely correlated. To create a safe and effective data transfer between the communicating nodes, a new censored regressive jaccard indexed certificateless signcryption (CEJICS) technique is suggested. Initially, the Gaussian likelihood censored regression is applied to identify the energy efficient node which supports enhancing the network lifetime. The security is implemented using the rabin cryptographic jaccard indexive certificateless signcryption (RCJICS). To create a signcryption system with the characteristics of digital signature and ciphertext authenticity, the proposed work focuses on certificateless cryptography. The NS-2 simulator is used for the simulation, and performance metrics are used to evaluate it. According to the observed quantitative results, the suggested CEJICS method outperforms the other conventional methods by improving the packet delivery ratio (PDR) by 93%, achieving a minimum drop of 7%, reducing delay by 22%, reducing overhead to 17%, minimizing energy consumption by 15%, and ultimately extending the network lifetime by 10%
Fuel consumption prediction of civil air crafts using deep learning: a comparative study
Full text linkAccurate fuel consumption prediction is critical for minimizing the adverse impact of fuel emissions on the environment, conserving fuel, and reducing flight costs. Additionally, precise fuel forecasting enhances trajectory prediction and supports effective air traffic management. This study evaluates the predictive performance of two deep learning techniques in predicting the fuel consumption of a civil aircraft belonging to Airbus A320NEO. Based on the analysis, the findings show that the deep neural network (DNN) model has better score of indicators and than the recurrent neural network (RNN) including mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE) and R-squared (R2). By integrating an automated feature selection approach with an optimized deep learning framework, this research contributes to the development of a robust and efficient predictive system for fuel consumption. The findings have practical implications for improving fuel management strategies in aviation, leading to cost savings and reduced emissions. One limitation of this study is its reliance on specific environmental variables, which may limit the model’s generalizability across different flight conditions, aircraft types, and operational scenarios
Metamaterial-enhanced four-port MIMO antenna for 5G communications at 28/38 GHz
Full text linkThis work presents a novel compact four-port multiple-in multiple-out (MIMO) antenna enhanced with metamaterial unit cells for 5G millimeter-wave (mmWave) applications at 28 and 38 GHz. Compact MIMO antennas at mmWave bands often suffer from high mutual coupling, which degrades isolation and diversity performance. To address this, the proposed design integrates metamaterial loading around each radiating element to effectively suppress coupling, enhance isolation, and improve overall efficiency. The antenna, measuring 27×27×0.8 mm³, is implemented on a flexible FR4_epoxy substrate (εr=4.4), enabling compatibility with portable and embedded devices. Full-wave simulations performed in both ANSYS high-frequency structure simulator (HFSS) and computer simulation technology (CST) studio suite confirm the effectiveness of the approach, achieving an exceptionally low envelope correlation coefficient (ECC) (0.0001), a fivefold reduction in channel capacity loss (CCL), and a wide impedance bandwidth of 25.90–34.93 GHz with |S11| below −10 dB in both operating bands. The design also exhibits stable directional gain and low sidelobes. Compared with recent compact MIMO antennas reported in the literature, the proposed configuration offers significantly improved isolation, bandwidth, and mechanical flexibility. These features make it a strong candidate for integration into high-capacity 5G modules, portable terminals, and compact internet of things (IoT) communication systems