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

31,377 Article Results

PMGHWO: A particle-guided adaptive grey wolf optimizer for large-scale traveling salesman problems

10.11591/ijece.v16i5.pp2819-2835
Hanadi A. Alshawabkah , Ayman Algafaan
The traveling salesman problem (TSP) remains challenging for metaheuristic algorithms, especially as the number of cities increases. This study proposes the particle-guided adaptive grey wolf optimizer (PMGHWO), which combines grey wolf optimizer (GWO)-based leadership guidance with crossover, particle-guided perturbation, and adaptive local refinement. PMGHWO was evaluated on ten TSPLIB instances and compared with grey wolf optimizer (GWO), genetic algorithms (GA), particle swarm optimization (PSO), whale optimization algorithm (WOA), and Harris Hawks optimization (HHO) under the same experimental conditions. The proposed method achieved shorter average tours on all tested instances, with reductions of 18.75% compared with GWO, 19.77% with HHO, 23.30% with GA, 39.08% with WOA, and 57.51% with PSO. Friedman and Wilcoxon tests confirmed significant differences between PMGHWO and the compared methods. The ablation study showed that adaptive refinement had the strongest effect on solution quality, while the influence of particle-guided perturbation and crossover varied across the benchmark instances. Although PMGHWO required more computation than the original GWO, its runtime remained competitive with several of the other methods. Overall, the results show that PMGHWO is a promising approach for TSP optimization and warrants further evaluation on larger and more complex combinatorial problems.
Volume: 16
Issue: 5
Page: 2819-2835
Publish at: 2026-10-01

A comparative study of standard PSO and adaptive fuzzy PSO for optimization

10.11591/ijece.v16i5.pp2720-2730
Paul Olujide Adebayo , Waheed Babatunde Yahya , Rasheed Gbenga Jimoh
In engineering, complex optimization problems often require efficient and reliable solution methods. An example of a metaheuristic algorithm is particle swarm optimization (PSO), which is widely used for its simplicity and adaptability. However, PSO performance is highly sensitive to parameter settings. To tackle this issue, researchers have developed adaptive variants, such as adaptive fuzzy particle swarm optimization (AF-PSO), that adjust parameters in real time during operation. In this study, standard PSO and AF-PSO are compared using several benchmark functions, Sphere, Rosenbrock, Rastrigin, Ackley, Griewank, and Schwefel, along with the multi-objective test problems ZDT1–3 and DTLZ1–2. Standard PSO was run with fixed parameters values (w=0.729, c₁=c₂=1.494) for the computation. The AF-PSO variant of PSO parameters are adaptively tune with a fuzzy inference concept. Each algorithm is evaluated across multiple independent runs to evaluate performance consistency. Across the test set, AF-PSO achieved superior performance in terms of solution quality and convergence. Among the benchmark functions, Griewank (+74.1%), Ackley (+65.4%), and Sphere (+63.0%) each have performances more than the others. Generally, the findings suggest that adapting parameters during the search improves convergence and solution quality, particularly for complex multimodal optimization problems.
Volume: 16
Issue: 5
Page: 2720-2730
Publish at: 2026-10-01

Real-time depth measurement and stability control of AUV using regression approximation and filtered pressure data

10.11591/ijece.v16i5.pp2417-2430
Senanjung Prayoga , Dhaniel Beny Wardhana , Ryan Satria Wijaya
This paper presents the development and experimental validation of a prototype-scale autonomous underwater vehicle (AUV) depth control system using a proportional-integral-derivative (PID) controller with depth feedback from a SEN0257 water-pressure sensor. Raw sensor readings are filtered and calibrated using linear regression, reducing the depth estimation error, as indicated by a decrease in root mean square error (RMSE) from 1.88 to 0.63 cm. The calibrated depth signal is implemented in real time as the feedback source for closed-loop control on the testbed. Controller performance is evaluated by comparing two tuning strategies: Ziegler–Nichols (ZN) closed-loop tuning and manual fine-tuning. Experiments were conducted at depth setpoints of 70 and 100 cm under consistent pool conditions, and additional trials were performed while the AUV executes forward motion to assess robustness under dynamic disturbances. System responses are quantified using rise time, overshoot, settling time, and steady-state error. Results show that calibration significantly improves sensor suitability for feedback, while the fine-tuned PID controller produces a more stable depth response with lower overshoot, smaller steady-state error, and shorter settling time than the ZN controller, despite the faster initial rise achieved by ZN tuning. Overall, combining calibrated pressure-based depth estimation with fine-tuned PID gains enables stable and accurate depth regulation for prototype AUV operation.
Volume: 16
Issue: 5
Page: 2417-2430
Publish at: 2026-10-01

Robust resource allocation in multi-cell UE-specific RIS-assisted D2D relay networks under imperfect CSI

10.11591/ijece.v16i5.pp2575-2594
Kayode Popoola , Ayodeji Ajani , Stuart Nicholson , Muheeb Ahmed , Srilatha Narayangari Pamuri , Ibrahim Bala Alhassan
Device-to-device (D2D) communication enhances spectral efficiency but remains constrained by limited transmission range, underlay interference, and the half-duplex overhead of conventional relays. User equipment-specific reconfigurable intelligent surfaces (UE-RIS) offer a promising alternative by enabling passive beamforming to strengthen D2D links without additional spectrum consumption. However, existing studies typically assume perfect channel state information (CSI) and single-cell operation, limiting their applicability to practical deployments. This paper proposes a robust multi-cell resource allocation (RMRA) framework for UE-RIS-assisted D2D relay networks under imperfect CSI. A hybrid uncertainty model is adopted, combining statistical Gauss-Markov CSI errors for intra-cell links with bounded norm-ball uncertainty for inter-cell links. The joint optimisation of resource reuse, transmit power allocation, and RIS phase configuration is formulated as a stochastic mixed-integer nonlinear program that maximises network spectral efficiency while satisfying outage and quality-of-service constraints. To efficiently solve the problem, a three-stage algorithm is proposed comprising distance-pruned Hungarian assignment, robust power control using Bernstein-type inequality and S-procedure based semidefinite programming, and soft actor-critic (SAC) based passive beamforming. Simulation results show that RMRA achieves a 94% D2D access rate at light load and over 75% at full load, improves sum spectral efficiency by 34.7% and 70.2% over AF relaying and direct D2D, respectively, attains 118.5 bits/s/Hz/W energy efficiency, and maintains 30.2 bits/s/Hz under severe CSI uncertainty.
Volume: 16
Issue: 5
Page: 2575-2594
Publish at: 2026-10-01

Temporal deep representation learning based remaining useful lifecyle prediction of electric vehicle lithium-ion batteries

10.11591/ijece.v16i5.pp2365-2378
Pradish Vaidya S. , Kevin Denzil V. , Monish S. , S. Cloudin , S. Saradha
In recent years, rapid growth of renewable energy systems and electric vehicle technologies has intensified the focus on lithium-ion batteries as critical energy storage components. Consequently, evaluating their performance and lifespan has become a significant concern in both scientific research and industrial applications. The accurate remaining useful life (RUL) prediction of lithium-ion batteries are major importance to increase energy management efficacy and increase the battery lifetime. Recently, the quick advancement of machine learning (ML) and artificial intelligence (AI) knowledge, data-driven approaches for forecasting the lithium-ion battery duration are involved extensive attention. Numerous researchers are employing deep learning (DL) approaches to make several techniques for predicting RUL, namely recurrent neural network (RNN) and convolutional neural network (CNN). This paper introduces a temporal deep representation learning based remaining useful Lifecyle prediction (TRDL-RULP) approach for electric vehicle lithium-ion batteries. The main goal of the TRDL-RULP framework is to support intelligent battery management methods and contribute to increasing the operational safety and lifecycle management of electric vehicle energy reserves systems. Initially, raw battery degradation data are processed using data normalization to eliminate scale variations and improve model stability. To enhance feature relevance and reduce dimensionality, a snake optimization-based feature selection strategy is employed to enable the extraction of the most informative degradation indicators. For RUL prediction, a long short-term memory autoencoder has been exploited to capture nonlinear temporal dependencies and extract robust latent representations. Finally, the tuna swarm optimization algorithm can be applied for optimal optimize parameters to improve convergence speed and predictive performance. The simulation study of the proposed TRDL-RULP algorithm is conducted using a benchmark lithium-ion battery degradation dataset obtained from the Kaggle repository. Extensive comparative results demonstrate the superior performance of the TRDL-RULP approach over recent methodologies.
Volume: 16
Issue: 5
Page: 2365-2378
Publish at: 2026-10-01

AI-based benchmarking framework for heterogeneous hospital pharmaceutical demand forecasting

10.11591/ijece.v16i5.pp2847-2857
Nendi Sunendar , Kursehi Falgenti , Farizal Gunawan
Accurate pharmaceutical demand forecasting is challenging because hospital medicine consumption exhibits heterogeneous patterns, including seasonal, volatile, and intermittent demand. This study proposes the regime-aware forecasting framework (RAFF), a reproducible benchmarking approach that combines structural demand diagnostics, leakage-controlled walk-forward validation, statistical comparison, and regime-stratified evaluation. Ten years of monthly demand records covering 300 pharmaceutical items were evaluated using Seasonal Naive, seasonal autoregressive integrated moving average with exogenous factors (SARIMAX), and long short-term memory (LSTM) models. Relative to Seasonal Naive, SARIMAX reduced mean absolute error by 18.20%, and root mean squared error by 20.58%, while LSTM reduced them by 16.48% and 21.75%, respectively. SARIMAX achieved the lowest aggregate mean absolute error, whereas LSTM achieved the lowest root mean squared error and greater stability as volatility increased. The results show that forecasting performance depends on demand structure, supporting regime-aware model selection for hospital inventory and procurement planning.
Volume: 16
Issue: 5
Page: 2847-2857
Publish at: 2026-10-01

BDLock: A blockchain-enabled two tier privacy-aware federated idam service platform using RBAC

10.11591/ijece.v16i5.pp2537-2548
Muhammad Shakil Pervez , Md. Nasim Adnan , Sarker Tanveer Ahmed Rumee , Moinul Islam Zaber
Centralized identity and access management (IDAM) systems suffer from sin-gle points of failure, lack of authorization transparency, and susceptibility to in-sider threats and privilege abuse. While role-based access control (RBAC) of-fers structured permission management, its enforcement through centralized pol-icy engines introduces auditability gaps unacceptable in modern distributed service delivery environments. This paper presents BDLock, a blockchain-enabled two-tier privacy-aware federated IDAM platform integrating OAuth 2.0, OpenID Connect (OIDC), and Hyperledger Fabric 2.4. The first tier validates JSON Web Tokens (JWT) issued by Keycloak against a Spring Boot resource server, the second tier enforces immutable scope-based RBAC rights on the Hyperledger Fabric ledger, ensuring every access decision is tamper-proof and auditable. Unlike prior approaches, BDLock uniquely bridges OAuth-authenticated off-chain identities to cryptographic on-chain Fabric wallet identities, satisfying all six STRIDE-modelled threats categories across both Web2 and Web3 identity models. Validated with up to 1,800 concurrent users, BDLock achieves a peak throughput of approximately 200 transactions per second using round-robin load balancing. At high concurrency, it outperforms single-peer fallback by up to 25%. Furthermore, it maintains uninterrupted access control during peer failures, eliminating the single point of failure found in all nine compared state-of-the-art systems.
Volume: 16
Issue: 5
Page: 2537-2548
Publish at: 2026-10-01

Impact of optimal power flow on power quality in a low voltage three-phase network: application to a real case in Lubumbashi (DR Congo)

10.11591/ijece.v16i5.pp2304-2320
David Milambo Kasumba , Guy Nkulu Wa Ngoie , Hyacinthe Tungadio Diambomba , Jean-Paul Katond Mbay , Bonaventure Banza WA Banza
Low-voltage distribution systems (LVDS) in rapidly growing Sub-Saharan African cities frequently experience severe phase imbalance, voltage deviations, and high technical losses due to overloaded and poorly balanced feeders. Despite the increasing availability of advanced optimization techniques, their application to real low-voltage networks in developing countries remains limited. This study investigates the impact of an unbalanced three-phase optimal power flow (OPF) framework on the power quality and operational performance of a real low-voltage distribution network located in Kamalondo, Lubumbashi (Democratic Republic of the Congo). The network model was parameterized using field measurements collected between September and December 2024. The optimization problem was formulated as a mixed-integer nonlinear programming (MINLP) model and solved using the interior point method implemented in Pandapower. The proposed framework simultaneously minimizes active power losses and mitigates phase imbalance while respecting voltage and thermal operating constraints. Simulation results demonstrate significant improvements in network performance. The minimum phase-to-neutral voltage increased from 198 V to 210 V, while the maximum voltage decreased from 232 V to 226 V, improving compliance with power quality standards. The maximum current phase was reduced by 15%, and total active power losses decreased by 30%. Furthermore, the voltage unbalance factor (VUF) was reduced from 8% to 3% through optimized phase allocation and power redistribution. These results demonstrate that unbalanced three-phase OPF constitutes an effective and practical solution for improving power quality, reducing technical losses, and enhancing the operational reliability of heavily loaded low-voltage networks in developing urban environments.
Volume: 16
Issue: 5
Page: 2304-2320
Publish at: 2026-10-01

Performance and quality analysis of brain MRI image transmission over free-space optical communication systems under severe atmospheric conditions

10.11591/ijece.v16i5.pp2526-2536
Entidhar Mhawes Zghair , Seham Hashem , Ali Hammadi
Reliable transfer of brain magnetic resonance imaging (MRI) data over atmospheric free-space optical (FSO) links is a key enabler of telemedicine, yet conventional FSO studies judge link quality by communication metrics such as the bit error rate (BER) alone, which cannot guarantee the structural and contrast fidelity that diagnosis demands. This study proposes a quality-aware FSO transmission framework for brain MRI in which link performance is assessed jointly through BER, peak signal-to-noise ratio (PSNR), and the structural similarity index (SSIM). A physical-layer FSO channel is modelled in OptiSystem 20 and co-simulated with MATLAB R2023b, which performs image serialization, reconstruction, and quality analysis. Thirty axial T2-weighted slices (256×256, 8-bit) from the public IXI dataset are transmitted at 1550 nm over clear-air, rain, and fog channels at 500, 1000, and 2000 m. Adopting conservative diagnostic thresholds of PSNR ≥ 30 dB and SSIM ≥ 0.85, the link is diagnostically usable in clear air at all tested distances (PSNR = 42.1 dB, SSIM = 0.98 at 500 m) and in rain up to 2000 m (PSNR ≥ 31.2 dB), whereas fog degrades quality below the thresholds at every distance, reaching PSNR = 22.7 dB and SSIM = 0.68 at 2000 m. A concatenated forward-error-correction (FEC) scheme is then shown to restore diagnostic quality under fog up to 1000 m, extending the usable fog range, while 2000 m remains infeasible and motivates hybrid FSO/RF operation. The framework provides quantitative deployment limits for FSO-based medical image transport.
Volume: 16
Issue: 5
Page: 2526-2536
Publish at: 2026-10-01

A comparative analysis of hybrid FFNN-LSTM and FFNN-RNN architectures for short term electricity load forecasting

10.11591/ijece.v16i5.pp2347-2356
Temitope Akinyede , Josephine Adenike Akinyede , Paul Kehinde Olulope , Emmanuel Taiwo Fasina , Temitope Adewale Olominu
Short-term accurate forecasting of electricity demand is crucial for power-system operation and energy scheduling and the equilibrium between electricity generation and consumption. The predicting of electric power consumption is however difficult because electricity-demand profiles are non-linear and time varying. In this paper, we consider two hybrid deep learning architectures feedforward neural network long short-term memory (FFNN-LSTM) and feedforward neural network recurrent neural network (FFNN-RNN) for multi-horizon electricity-load forecasting. The architectures we proposed combine the ability of FFNN to represent data non-linearly with the sequential modelling capability of LSTM and RNN. The authors assess the models based on historical electricity-load observations from Ado-Ekiti, at three different forecasting horizons of 24 hours, 72 hours, and 168 hours. Root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) assessed predictive performance. The findings reveal that FFNN-LSTM achieves a consistently lower RMSE across the evaluated horizons, resulting in greater effectiveness to confine relatively large forecasting errors. On the other hand, the separate LSTM and RNN models achieve lower MAE and MAPE in various scenarios, suggesting stronger short-term reaction to electricity demand. The results, therefore, show a trade-off between forecast stability and sensitivity to rapid load changes. In general, the performance of hybrid architecture is more stable compared to the standalone recurrent models which are more responsive to short-term changes when we look at most of the forecasting horizons. According to the research paper, the forecasting architectures can now be selected for smart grid applications.
Volume: 16
Issue: 5
Page: 2347-2356
Publish at: 2026-10-01

Design science research in developing a religious chatbot based on Bulugh al-Maram

10.11591/ijece.v16i5.pp2782-2794
Aris Tjahyanto , Irmasari Hafidz , Faizal Johan Atletiko
Chatbots have recently gained significant popularity. For instance, ChatGPT has become a preferred tool for many individuals seeking instant answers without relying on human responses. This immediacy sets chatbots apart from books, which require users to search for information manually. This time-consuming process does not align with millennials' preference for convenience and efficiency. Studying hadith independently using the Bulugh al-Maram book demands considerable time and effort. The limited use of natural language processing technologies in religious chatbots restricts their ability to handle complex inquiries effectively. A chatbot capable of answering hadith-related questions could greatly assist the public in studying hadith texts by providing direct responses without extensive searching. This chatbot was designed for web browsers, utilizing deep learning as its core technology. This research led to the development of a chatbot prototype for learning hadith from Bulugh al-Maram. Built using the design science research (DSR) methodology, the prototype achieves an intent recognition rate (IRR) of 86.82%. However, its capabilities are below the BERT model, demonstrating a strong ability to accurately interpret user questions and statements.
Volume: 16
Issue: 5
Page: 2782-2794
Publish at: 2026-10-01

Information architecture debt: Why legacy platform schema decisions constrain enterprise AI capability

10.11591/ijece.v16i5.pp2473-2482
Mihir Shah
Enterprise platforms accumulate a specific category of technical debt this paper terms information architecture debt. Schema decisions optimized for transactional efficiency in earlier computing eras produce structural constraints that limit what artificial intelligence can accomplish on those platforms, largely independent of which models are selected or how they are orchestrated. This paper positions information architecture debt as a category distinct from code debt and infrastructure debt, and it argues that the distinction matters because remediation locality and coordination cost differ sharply. A five-indicator diagnostic framework is proposed, covering duplicate canonical entities, broken semantic chains, provenance gaps, enforcement asymmetry, and consumer assumption divergence. The framework supports a capability ceiling hypothesis: substrate defects impose an upper bound on AI outcomes that no model choice appears able to exceed. A sequenced remediation approach follows, prioritizing entity resolution, semantic alignment, and provenance instrumentation by AI-capability impact rather than ease of fix. Grounded in practitioner experience structuring enterprise information architecture across multi-language, multi-system platforms, the framework offers leaders diagnostic and sequencing tools, and it establishes a conceptual foundation for later quantitative and sector-specific refinement.
Volume: 16
Issue: 5
Page: 2473-2482
Publish at: 2026-10-01

Predictive and fault-tolerant virtual machine migration for energy-efficient cloud data centers

10.12928/telkomnika.v24i5.27706
Rakshan; Sri Venkateswara College of Engineering G. K. , P.; Sri Venkateswara College of Engineering Vinothiyalakshmi
Virtual machine (VM) migration is a key mechanism for improving energy efficiency, service continuity and reliability in cloud data centers. However, conventional migration strategies are largely reactive and fail to account for workload fluctuations and potential failures, often resulting in inefficient resource utilization and increased service-level agreement (SLA) violations. This paper proposes the predictive VM migration manager (PVMM), a unified framework that integrates workload forecasting and failure prediction for proactive migration control. PVMM combines a gated recurrent unit (GRU)-based model for short-term resource prediction with a machine-learning-based failure predictor to identify high-risk VMs. An adaptive dynamic threshold based on energy consumption (ADT-EC) detects host overload conditions, while an improved energy-aware best-fit (IEABF) heuristic selects optimal migration targets. Experimental results demonstrate that PVMM reduces unnecessary migration, improves SLA compliance and enhances overall energy efficiency and system reliability. These findings highlight the effectiveness of predictive, multi-objective migration strategies for next-generation cloud data center management.
Volume: 24
Issue: 5
Page: 1513-1525
Publish at: 2026-10-01

Rainfall detection on a tropical island using a communication satellite downlink signal and artificial intelligence models

10.12928/telkomnika.v24i5.26012
Raden Yudha; Badan Meteorologi Klimatologi dan Geofisika Mardyansyah , Budhy; Universitas Indonesia Kurniawan , Santoso; Universitas Indonesia Soekirno , Danang; Badan Meteorologi Klimatologi dan Geofisika Eko Nuryanto , Ferry; Universitas Negeri Jakarta Budhi Susetyo
The development of rainfall estimates based on satellite links in several high latitude regions shows good results. However, its development for tropical regions is still very less promising, leaving the question of which method is worth using. In this work, we investigate artificial intelligence (AI) models by utilizing the Ku-band satellite downlink signal for rainfall detection on a tropical island. Long-term evaluation of all the models is performed using one year of rainfall intensity data. The findings of this study demonstrate that one-dimensional convolution neural network (1DCNN), long short-term memory (LSTM), and random forest (RF) models can effectively identify rainfall occurrences on tropical islands, with the area under the receiver operating characteristic curve (ROC) value of 0.84, 0.84, and 0.83, respectively. These three models consistently provide better accuracy in detecting the region’s diverse rainfall patterns throughout the year. The 1DCNN has better performance compared to the other models, achieving accuracy values of 0.76 and 0.82 during the periods of lowest and highest rainfall, respectively. Considering the presence of numerous potential mislabeled rain samples in the dataset, this result is excellent. In addition, the utilization of higher resolution rainfall intensity data can be a great potential for real-time rainfall monitoring in the tropical region.
Volume: 24
Issue: 5
Page: 1632-1643
Publish at: 2026-10-01

Label-free acoustic monitoring of honeybee swarming: An unsupervised online learning approach

10.11591/ijece.v16i5.pp2483-2493
Abdelmadjid Guessoum Graba , Djoher Dalila Graba
Colony losses caused by honeybee swarming remain a major operational chal lenge because departure occurs within minutes, although acoustic changes be gin tens of minutes earlier and could allow timely intervention if detected reli ably. Current detection systems miss this window because the circadian rhythm of individual hive acoustics is not modelled, making it impossible to separate genuine pre-swarming drift from normal day-to-night spectral variation. Re cursive least squares is used to estimate a colony-specific circadian baseline, Mahalanobis distance scoring is applied to quantify deviations, and BOCPD ac cumulates Bayesian evidence of a regime shift, with a threshold derived from warmup data guaranteeing a controlled false alarm rate without labelled record ings and regardless of bee race, season, or microphone placement. A controlled simulation was used for evaluation, yielding 3.5× higher precision than the best label-free baseline, swarm anticipation exceeding 25 minutes before departure, and a false alarm rate held at the nominal 5% target. The low per-frame cost and memory footprint make this algorithm deployable on resource-constrained embedded devices, enabling continuous autonomous hive monitoring without expert supervision.
Volume: 16
Issue: 5
Page: 2483-2493
Publish at: 2026-10-01
1 2 3
...
2091 2092
Show 4 of 2092

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