TELKOMNIKA (Telecommunication Computing Electronics and Control)
Not a member yet
3120 research outputs found
Sort by
Enhancing handover management in 5G networks with encoder-decoder LSTM for multistep forecasting
Full text linkThe continuous evolution of wireless communication networks, fueled by advancements in 5G and the envisioned potential of 6G technologies, has introduced significant challenges in mobility management and handover (HO) optimization. The frequent HOs due to network densification, particularly at high frequencies like millimeter waves (mmWave) and terahertz (THz) bands, can lead to increased latency, and potential service disruptions. To address these issues, artificial intelligence (AI) driven approaches are emerging as promising alternatives. This paper explores the use of deep learning techniques for predictive HO management. An encoder-decoder long short-term memory (ED-LSTM) model is proposed to generate multistep predictions of future reference signal received power (RSRP) values. The model was trained and evaluated on two distinct real-world drive-test datasets. The results demonstrate that the proposed ED-LSTM model achieves lower prediction error, with a mean absolute error (MAE) of 2.07 for dataset 1 and 2.33 for dataset 2, and a mean absolute percentage error (MAPE) of 2.80% for dataset 1 and 2.96% for dataset 2. Overall, the ED-LSTM outperforms the bidirectional LSTM (BiLSTM) and standard LSTM (S-LSTM) model, achieving improvements of 33–38% on dataset 1 and 48-50% on dataset 2 in terms of MAE and MAPE, respectively
A hybrid ARIMA and DNN approach with residual learning for electric vehicle charging demand forecasting
Full text linkThe rapid growth of electric vehicle (EV) adoption has created significant challenges for power grid management and charging infrastructure planning. Accurate forecasting of EV charging demand is therefore essential to ensure reliable electricity supply and effective station deployment. This study proposes a novel hybrid forecasting framework that combines autoregressive integrated moving average (ARIMA) with deep neural networks (DNN) through a residual learning strategy. In this approach, ARIMA models the linear temporal patterns, while DNN captures the nonlinear residuals, resulting in improved efficiency and predictive accuracy. The proposed hybrid model is one of the first applications of the residual learning approach for EV demand forecasting in Indonesia. Experimental evaluation using real-world daily consumption data shows that the hybrid method achieved the highest prediction accuracy of 98.22%, consistently outperforming single-model baselines. Beyond technical performance, the model can support stakeholders in planning charging infrastructure and help maintain grid stability in rapidly growing EV ecosystems
Retrieval-augmented generation for Arabic legal information: the family code case study
Full text linkThis document describes the implementation and evaluation of a retrieval-augmented generation (RAG) system to improve access to and understanding of Moroccan law, particularly the family code in Arabic. The research addresses the drawbacks of the widely used linguistic model applied to complex legal terminology in Arabic and aims to help citizens access crucial legal data. We built a new custom dataset with 2.5 k question-answer pairs while preprocessing and using the BGE-m3 embedding model in this experiment. Performance metrics, such as mean reciprocal rank (MRR), Recall@k, and F1-score, indicate that the RAG approach is effective compared to the use of standalone large language models (LLMs). Moreover, an evaluation on metrics such as the blue score, fidelity, response relevance, and contextual relevance indicated that the matching of meanings and context were well captured, which signifies a very good semantic understanding. The research highlights the need for language-specific model specialization in Arabic and presents its main challenges, such as dialectal variations and appropriate evaluation measures. The results indicate that well-developed RAG systems offer a promising approach to improving access to legal information in Arabic-speaking practice communities and to guiding future research and development in this field
Performance of piezoelectric energy harvesters at various angles
Full text linkPiezoelectric materials are capable of generating electricity in response to mechanical strain, making them suitable for energy harvesting applications. Piezoelectric energy harvesters (PEHs) are promising alternatives for renewable energy generation, particularly because mechanical strain can be induced in various ways, including utilizing wind flows. This study investigates the performance of a PEH integrated with a laboratory-scale wind-driven micro-windmill. The experiment is carried out by rotating blades of the windmill intermittently; thus, it contacts the PEH, inducing oscillatory motion and generating strain, which finally produces electricity. The configuration angle is varied with 30°, 45°, and 60° to produce variation of power output analyzed in this study. The results demonstrate that a lower configuration angle, specifically 30°, produces the highest voltage near 1.4 V. This is due to the alignment of the applied force with the natural bending direction of the cantilever, resulting in greater induced strain and increased voltage output. Conversely, increasing the configuration angle reduces the effectiveness of force induced to PEH, diminishing strain induction and electrical generation, which only about 1.2 V. The finding of this study can potentially contribute to advance the design and optimization of PEHs for renewable energy applications, particularly in powering microelectronic devices
Performance enhancement of PV generator using a sensor based dual axis solar tracking system in Algeria
Full text linkThis article presents the implementation of a two-axis solar tracking system and its impacts to increase the performance of the photovoltaic system in northern Algeria. The system enhances the efficiency of solar systems by optimizing their exposure to sunlight making the sunbeam perpendicular to solar panel. The main objective of the study is to develop a technically proficient and economically viable solution to increase solar energy production. The design relies on integrating light sensors and motors controlled by an Arduino board, enabling automatic adjustment of solar panel positions. This approach offers dynamic and precise orientation, based on light dependent resistor (LDR) sensor design and threshold value, resulting in a significant increase in energy output. The results show that the dual-axis solar tracking system can capture 60.64% more solar energy, taking into account the power consumption of the two electric actuators. The findings of this study will positively influence the promotion of clean and sustainable energy sources while providing a practical solution for more efficient utilization of solar energy in Algeria
Novel fractional order sinusoidal oscillators using operational trans resistance amplifier
Full text linkThe design of fractional order circuits in very large-scale integration (VLSI) domain is gaining the interest of many researchers. At the same time design of fractional circuits using the current mode devices is attracting the research community. In this paper, several possible fractional order sinusoidal oscillators using operational trans resistance amplifier (OTRA) as a basic building block is presented. The necessary condition for the frequency of oscillation and condi tion for oscillations is derived. Fractional order operator sα is the most crucial one to be approximated. In this paper, the fractional order element is approxi mated by the continued fraction expansion (CFE). The approximation is carried out up to fifth order. The circuits are tested with the simulation software named LTspice. The results agree with the theoretical one. The proposed circuits of fers a frequency of 15 MHz, 20 MHz, and 25 MHz which is higher in value as compared to the existing circuits. The proposed circuits finds applications in bio medical, communication circuits
Deep learning-based image super-resolution using generative adversarial networks with adaptive loss functions
Full text linkThis study investigates deep learning based single image super-resolution (SISR) and highlights its revolutionary potential. It emphasizes the significance of SISR, and the transition from interpolation to deep learning driven reconstruction techniques. Generative adversarial network (GAN)- based models, including super-resolution generative adversarial network (SRGAN), video super-resolution network (VSRResNet), and residual channel attention-generative adversarial network (RCA-GAN) are utilised. The proposed technique describes the loss functions of the SISR models. However, it should be noted that the conventional methods frequently fail to recover lost high-frequency details, which signify their limitations. The current visual inspections indicate that the suggested model can perform better than the others in terms of quantitative metrics and perceptual quality. The quantitative results indicate that the utilised model can achieve an average peak signal-to-noise ratio (PSNR) enhancement of X dB and an average structural similarity index (SSIM) increase of Y. A range of improvements of 7.12-23.21% and 2.75-10.00% are obtained for PSNR and SSIM, respectively. Also, the architecture deploys a total of 2,005,571 parameters, with 2,001,475 of these being trainable. These results highlight the model’s efficacy in maintaining key structures and generating visually appealing outputs, supporting its potential implications in fields demanding high-resolution imagery, such as medical imaging and satellite imagery
Rate-splitting multiple access in satellite-terrestrial communication systems: performance analysis
Full text linkThis paper investigates the throughput and outage probability (OP) of rate splitting multiple access (RSMA) in satellite–terrestrial communication networks. By dividing user messages into common and private parts, RSMA enhances spectral efficiency and user fairness while addressing hardware impairments and co-channel interference. The proposed hybrid system model is analyzed and compared with non-orthogonal multiple access (NOMA) under various power allocation coefficients and channel conditions. Results show that RSMA achieves lower OP and higher throughput than NOMA, particularly in dense multi-cell deployments. Numerical evaluations further demonstrate RSMA’s robustness against interference and hardware limitations, underscoring its potential as a reliable solution for next-generation satellite–terrestrial relay networks
Indonesian continuous speech recognition optimization with convolution bidirectional long short-term memory architecture
Full text linkSpeech recognition can be defined as converting voice signals into text or lines of words by using algorithms implemented in computer programs. There are several types of speech recognition, including recognition for isolated word speech, continuous speech, spontaneous speech, and conversational speech. Research on continuous speech recognition, especially in Indonesian, has been developed using both stochastic methods such as Hidden Markov model (HMM) and deep learning methods. Currently, deep learning approaches are more widely used in speech recognition applications. This research optimizes Indonesian speech recognition by adding convolution layers to the bidirectional long short-term memory (Bi-LSTM) architecture. The goal of this research is to find the best architecture so that better Indonesian continuous speech recognition results can be obtained. The dataset used in this research was created by the intelligent systems research group in the Department of Informatics at Universitas Diponegoro. All speakers who participated in this dataset came from five ethnic groups in Indonesia, representing the dialects of their respective ethnic groups. The research results show that by adding a convolution layer to the Bi-LSTM architecture, speech recognition performance increases significantly with an average word error rate (WER) reduction of 15.56% compared to using only the Bi-LSTM architecture
Implementation of ICMP flood detection and mitigation system based on software-defined network and sFlow-RT
Full text linkThis study evaluates internet control message protocol (ICMP) flood detection and mitigation in software-defined networks (SDN) using an SDN architecture with sFlow-RT for real-time traffic monitoring. OpenFlow switches and sFlow agents detect malicious patterns, following the prepare, plan, design, implement, operate, optimize (PPDIOO) methodology. Unlike prior approaches, this system leverages SDN programmability and sFlow-RT’s real-time analytics to reduce ICMP packets from 311,130.2 to 99 and latency by 80%, outperforming traditional methods in speed and responsiveness. It ensures network availability, with practical benefits for large-scale networks like internet service providers (ISPs). However, sFlow sampling rates may affect accuracy in high-speed networks, and a single OpenDaylight (ODL) controller limits generalizability. Future work should test alternative controllers and extend to other DDoS types like user datagram protocol (UDP) floods in diverse topologies