Amirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101A Bibliographic and Qualitative Analysis on Navigation Concepts of Mobile Robots330589310.22060/eej.2025.24755.5759ENMelikaAtaollahiElectrical Engineering, Iran University of Science and Technology, Tehran, IranMohammadFarrokhiElectrical Engineering, Iran University of Science and Technology, Tehran, Iran0000-0002-8431-4650Journal Article20250916With the advent of robots in humans’ life, such as self-driving cars and unnamed aerial vehicles, developing effective methods to improve the performance of these autonomous systems has become one of the most attractive research areas in recent years. One of the most fundamental challenges of mobile robots is applying and developing an appropriate and effective navigation strategy. The concept of navigation deals with subjects such as finding the current position in the environment, planning appropriate actions to reach the target, and controlling the actuators to track the desired actions. Therefore, the concept of navigation has different aspects, and the promotion of these aspects leads to the development of good guidance for autonomous robot systems. The first step in developing the navigation unit is identifying the related and correlated areas. This article performs a bibliographic analysis on the development rate, finding sources, and high-occurrence keywords. The required data are obtained from the Scopus database between 2015 and 2025. The most frequent keywords in the last eight years specify the most effective and relevant areas in the concept of navigation. Then, by qualitatively examining the most important keywords, the current position, challenges, and progress are determined.https://eej.aut.ac.ir/article_5893_c950cde9b3f83f41721788e3315a14a3.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101ANFIS Granger Causality for Estimating Effective Brain Connectivity and Mutual Information for Connectivity Type Determination Using MEG and EEG Data: Application to Epilepsy3144590710.22060/eej.2025.23832.5645ENErfanVajdiSchool of Electrical and Computer Engineering, University of Tehran, Tehran, Iran.0009-0001-5447-0249MortezaFattahiSchool of Electrical and Computer Engineering, University of Tehran, Tehran, Iran.0000-0002-3807-4449HamidSoltanian-ZadehSchool of Electrical and Computer Engineering, University of Tehran, Tehran, Iran.0000-0002-7302-6856Journal Article20250315In the scientific community, it is well established that the brain is linked to neural disorders such as epilepsy, Alzheimer's, and depression, all of which can affect neural connectivity. These conditions can disrupt communication between different brain regions. To assess these changes, neuroscientists measure neural signals like EEG and MEG and analyze brain connectivity through scalp recordings. Various methods have been developed to evaluate intra-brain connectivity, including classical techniques such as Granger causality (GC), Mutual Information (MI), Directed Transfer Function (DTF), and Dynamic Causal Modeling (DCM). Recently, there has been increasing interest in applying neural networks as a modern approach across various fields. However, many existing methods suffer from low precision. This paper proposes the Adaptive Neuro-Fuzzy Inference System Granger Causality (ANFISGC) as a solution for measuring effective connectivity using EEG and MEG data. Our approach integrates symplectic geometry, ANFIS regression, and Granger causality, allowing for the detection of both linear and nonlinear causal information flow. This multivariate method can also differentiate between direct and indirect connectivity, enhancing its significance. Additionally, we utilized Mutual Information (MI) to evaluate the relationship between two variables, offering insights into the linearity or nonlinearity of connectivity. This measurement provides a further understanding of brain functionality. To assess the effectiveness of our approach, we conducted tests using simulated data and data from five epilepsy patients. The results show that measurements based on MEG data align well with clinical findings, while incorporating EEG data alongside MEG (in a multimodal approach) does not improve the results.https://eej.aut.ac.ir/article_5907_5bcf8dd060e5ea0bff484b4a4127cb47.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Efficient Control and Five-Level MMC Integration for Power Quality Improvement in DFIG-Based Wind Energy System4558586610.22060/eej.2025.24305.5677ENKuncheGowthamiDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology, Rajahmundry, India.DondapatiRavi KishoreDepartment of Electrical and Electronics Engineering, Godavari Global University, Rajahmundry, India.0000-0002-2567-2888Inti SaiDeepthiDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology, Rajahmundry, India.KolapatiDurga PrasadDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology, Rajahmundry, India.GandhamSatish KumarDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology, Rajahmundry, India.Journal Article20250621Main objectives of the study are to address Power Quality (PQ) problems caused by shifting load demands, including voltage instability and harmonic distortion, which affect system performance and reduce stability. In order to achieve the set goals, the following tasks were accomplished: the design and implementation of a 5-Level Modular Multilevel Converter (MMC) powered by a Double Fed Induction Generator (DFIG)-based wind system, the application of advanced control techniques utilizing D-Q theory and a Hysteresis Current Controller (HCC) for stable current injection, and the incorporation of an LC filter to enhance AC supply quality. The most important results are the reduction of total harmonic distortion (THD) to 1.35%, enhanced voltage stability, and improved overall PQ, validated through MATLAB simulations. The significance of obtained results is the development of a robust and efficient system that addresses PQ issues, offering a substantial improvement over state-of-the-art methods and ensuring high-quality power delivery to grid.https://eej.aut.ac.ir/article_5866_a7471fdc77b3435276507cc8f2dc2569.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Hilbert-Mel Frequency Spectrum Features for Efficient EEG-Based Alzheimer’s Detection5974588710.22060/eej.2025.24329.5685ENMaryamBahmaniFaculty of Electrical Engineering, Shahrood University of Technology, IranHosseinMarviFaculty of Electrical Engineering, Shahrood University of Technology, IranHosseinKhosraviFaculty of Electrical Engineering, Shahrood University of Technology, IranVahidAbolghasemiSchool of Computer Science and Electronic Engineering, University of Essex, Colchester, UKJournal Article20250629Alzheimer's disease (AD) is a progressive neurodegenerative disorder that severely impairs cognitive function and disrupts brain connectivity. Early and accurate diagnosis is crucial for effective intervention, yet identifying discriminative features from complex electroencephalography (EEG) signals remains a challenge. Resting-state EEG provides a non-invasive and cost-effective tool for AD detection, but its diagnostic utility is highly dependent on the quality of extracted features. This study introduces a novel feature extraction approach that uses Mel-Frequency Spectrum Features (MFS) and the Hilbert Transform (HT) to enhance both spectral and temporal feature representation of EEG signals. The proposed Hilbert-Mel Frequency Spectrum (HMFS) framework captures subtle variations in phase and amplitude, providing a rich and complementary set of descriptors. Principal Component Analysis (PCA) is employed to reduce dimensionality while retaining key information, enabling more efficient and accurate classification. A 5-fold cross-validation approach was employed to assess model performance and generalizability. The extracted features are classified using various machine learning models, with K-Nearest Neighbors (KNN) achieving the highest performance. The proposed method reached an accuracy of 99.24% with a perfect recall of 100%, precision of 98.61%, specificity of 98.39%, F1-score of 99.30%, and geometric mean score of 99.31%. Compared to existing EEG-based AD detection techniques, the HMFS method surpasses previous approaches in accuracy and recall and the method achieves higher performance. The integration of spectral and temporal features results in a more robust feature space, thereby improving generalization. This approach provides a reliable, efficient framework for early AD diagnosis with potential clinical applications.https://eej.aut.ac.ir/article_5887_7cfd5df443b4eb0d69886a583b33de4c.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Hybrid Deep Learning and Evolutionary Feature Selection for Real-Time Product Recommendations75100591110.22060/eej.2025.24679.5746ENLazarusNisha Evangelin1Department of Computer Science and Engineering, Noorul Islam Centre for Higher Education, Kanyakumari, Tamil Nadu, India.0009-0001-9226-4999RavichandranDeviDepartment of Artificial Intelligence and Data Science, R.M.K Engineering College, Kavaraipettai, Tamil Nadu 601206, India.601206, IndiaSundar RajBharathiDepartment of Electrical and Electronics Engineering, S.A Engineering College, Chennai, 600077, India.VallirathiIyyaduraiRohini college of Engineering and Technology, Anjukramam, Tamil Nadu, India.ShyamalagowriMurugesanDepartment of Electrical and Electronics Engineering, K.S.Rangasamy College of Technology, Tiruchengode, India.JehanChelliahDepartment of Computer Science and Engineering, Vel Tech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College, Avadi, Chennai-62, India.Journal Article20250904The swift expansion of e-commerce has driven the creation of Recommendation Systems (RS) that help users navigate vast catalogues and make informed purchase decisions. This work presents a novel recommendation system framework integrating adaptive techniques for enhanced accuracy and efficiency. The system utilizes Adaptive Evolutionary Feature Selection (AEFS), a novel feature selection algorithm combining genetic algorithms and reinforcement learning to select the most relevant features from user interaction data, product details, and contextual data. The pre-processing stage comprises text tokenization, normalization, and stop-word removal, followed by feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Factor Modelling. User profiling is performed using Graph-based Profiling and Behavioural Profiling, allowing for a holistic view of user inclinations and preferences. The Bidirectional Encoder Representations from Transformers for Recommendations (BERT4Rec) model, which uses transformer-based architectures, is used for generating recommendations by capturing complex sequential relationships in user behaviour. This hybrid approach combines Collaborative Filtering (CF) and Content-based Filtering (CBF) to deliver accurate and personalized recommendations. Real-time recommendations are provided using a distilled model, ensuring scalability and efficiency for large-scale e-commerce platforms. The system continuously adapts through a feedback loop based on user interactions, using reinforcement learning to improve performance. With an accuracy of 98%, BERT4Rec achieves improvements of up to 18.45% across key metrics. The proposed framework enhances recommendation accuracy, achieves a feature reduction rate of 70%, and ensures a robust user experience in modern e-commerce environments.https://eej.aut.ac.ir/article_5911_84a955d5ff75f508ec01007bc2b9b301.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Advanced State of Health Estimation for Lithium-Ion Batteries Using Deep Learning and Feature Engineering101120591510.22060/eej.2025.24863.5779ENNegarKhaliliDepartment of Electrical Engineering, K. N. Toosi University of Technology, Tehran, IranSaeedKhankalantaryDepartment of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran0000-0002-1028-8306AliNajafi ArdekanyDepartment of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, IranJournal Article20251006Obtaining an accurate estimate of the state of health of a lithium-ion battery is important for its efficiency and stability, but it's hard because the aging processes are so complicated and non-linear. Deep neural networks and long short-term memory networks are powerful tools, but their potential is often not realized if the raw operating features fail to capture synergistic aging mechanisms. This article proposes a novel two-stage hybrid feature engineering methodology to address this constraint. In the first stage, the method uses a binary particle swarm optimization algorithm to look for a small set of important predictive features. In the second stage, the parsimonious subset is enhanced with a physics-constrained Electro-Thermal Interaction Feature that incorporates terminal voltage and temperature interaction stresses. The resulting feature set was subsequently utilized for the training and evaluation of both deep neural networks and long short-term memory networks models. Adding the electro-thermal interaction feature significantly improves the predictability of both models on the primary B05 cell, raising the R² value from about 0.93 to over 0.99. To assess generalizability, the framework was rigorously validated using a cross-battery approach on two additional cells (B07 and B055), where the models maintained high performance with an average R² > 0.97. The findings indicate that domain-knowledge-intensive feature engineering significantly influences performance more than the architectural decision between deep neural networks and long short-term memory networks, facilitating highly accurate and robust state of health predictions, which are crucial in advanced battery management systems.https://eej.aut.ac.ir/article_5915_9ba196c7a6e89eafd0954de80fc1b224.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101From DC to Holistic Centrality: AI-Driven Estimation for Enhanced Power Network Analysis121148581910.22060/eej.2025.24278.5667ENMohammadShahraeiniDepartment of Electrical Engineering, Faculty of Engineering, Golestan University, Gorgan, Iran0000-0003-2249-426XMasoudBesharatlooDepartment of Electrical Engineering, Faculty of Engineering, Golestan University, Gorgan, Iran0009-0001-1024-3204Journal Article20250611This paper introduces a novel approach to power system analysis by integrating DC Holistic Centrality with advanced deep learning (DL) techniques to enhance the efficiency and accuracy of grid operation assessments. We propose DC Holistic Centrality, a computationally efficient measure derived from DC load flow data, which extends traditional operational centrality by incorporating generation and demand nodes as pendant buses. Leveraging this new metric, we develop a suite of AI-driven estimation methods: a linear regression baseline for active holistic betweenness prediction, a deep neural network (DNN) for accurate cross-bus prediction of active holistic betweenness, a convolutional neural network (CNN) for voltage magnitude estimation from DC holistic dependency matrices, and a scalability assessment using the IEEE 57-bus system to validate model robustness. The study utilizes a comprehensive dataset generated from varied operational scenarios, with feature selection guided by correlation analyses rather than additional extraction techniques. Results demonstrate significant improvements in capturing inter-bus dependencies and system dynamics, offering a promising framework for real-time grid monitoring and management.https://eej.aut.ac.ir/article_5819_8e036cc193d0af59aa9b22821248292b.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Reinforcement Learning-Tuned Fractional-Order Sliding Mode Control for Load Frequency Stability in Power Systems149166588110.22060/eej.2025.24314.5680ENFarhadAmiriDepartment of Electrical Engineering, Tafresh University, Tafresh, Iran.0000-0001-9335-7823Journal Article20250624Power systems can improve their frequency stability by using the load-frequency control (LFC) system. Power system parameter unpredictability and unforeseen load disruptions complicate and test the LFC system's performance. The goal of this work is to increase the frequency stability of a two-area power system by constructing the fractional-order sliding mode controller (FOSMC) inside each area's LFC structure. The controller is combined with reinforcement learning (RL) to further enhance the FOSMC's performance against disturbances and parameter uncertainty. The primary objective of this control strategy is to enhance dynamic performance and reduce frequency oscillations in the face of unforeseen load interruptions and uncertainty in all power system components. The performance of the SMC is improved by utilizing fractional derivatives in the sliding surface, which successfully reduces chattering and raises the frequency stability of the two-area power system. The performance of the suggested method is assessed in the context of LFC for power systems under various situations by contrasting it with alternative control strategies, such as PDSMC, SMC and Fuzzy-RL. The findings show that the suggested method (FOSMC-RL) significantly improved the frequency stability of the two-area power system. Additionally, the suggested approach shows resilience to high power system parameter uncertainty and severe abrupt load disruptions.https://eej.aut.ac.ir/article_5881_6d378765f17a856b7ba8bf1541cafb69.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Electric–Thermal Sector Coupling with Hybrid Renewables and Storage for Sustainable Rural Energy Systems167188588910.22060/eej.2025.24451.5707ENElhamSadeghiDepartment of Electrical Engineering, University of Science and Technology of Mazandaran, Behshahr, IranMostafaGholamiDepartment of Electrical Engineering, University of Science and Technology of Mazandaran, Behshahr, Iran
Technology of Mazandaran, Behshahr, IranJournal Article20250802With the increasing importance of electrical energy in daily life, power outages pose serious challenges. Globally, efforts are made to ensure access to electricity for all, especially in rural areas that are often remote. Similar difficulties exist in meeting thermal loads, often addressed through natural gas networks—solutions that are costly and logistically complex. This paper investigates the strategic integration of hybrid renewable energy systems and storage technologies to enable sector coupling, thereby allowing coordinated management of both electrical and thermal loads in rural regions. By utilizing sector coupling, the proposed approach improves energy efficiency, decreases fossil fuel dependence, and supports sustainable development. Thermal load control is employed as an interface between electrical sources and thermal demand, increasing the share of renewables. The study begins by analyzing various off-grid hybrid energy system models and then evaluates the impact of factors such as natural gas prices, system reliability, costs, and emissions. Additionally, a sensitivity analysis on declining battery investment costs is conducted to assess their influence on system economics and renewable penetration. A comparative benchmark using a natural gas generator with heat recovery is also examined to highlight the techno-economic advantages of the proposed system configuration. Results show that deploying off-grid hybrid systems and accepting a degree of reduced reliability can notably increase the contribution of renewables in supplying simultaneous electric and thermal loads. This shift leads to significant reductions in pollutant emissions and fosters sustainable rural development—achieved without the prohibitive expenses tied to expanding electricity and gas infrastructure.https://eej.aut.ac.ir/article_5889_a3bf6e4db673b6449c2f7d13ee6ec9c0.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Design of Three-Phase Grid-Connected PV System with Z-Source Boost Converter and Neural Network-Based Harmonic Elimination189204590810.22060/eej.2025.24499.5717ENBKavya Santhoshi1Department of Electrical & Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India.0000-0002-5309-8158DondapatiRavi KishoreDepartment of Electrical & Electronics Engineering, Godavari Global University, Rajahmundry, India.0000-0002-2567-2888Md.Shoaib AkhterDepartment of Electrical & Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India.AsifIqubalDepartment of Electrical & Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India.AshrafAliDepartment of Electrical & Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India.Journal Article20250731The progress towards Renewable Energy Sources (RESs) has highlighted the crucial role of Photovoltaic (PV) systems in meeting the energy demands of the world. As energy from PV system becomes significant, there is need for efficient and high quality grid systems becomes essential. As a consequence, this research proposes a grid connected PV system to address the challenges by integrating Z-Source Boost Converter (ZSBC) and neural network based controller for eliminating harmonics. The ZSBC is employed to overcome the limitations of conventional DC-DC converters, offering greater flexibility in voltage boosting and improved reliability in power conversion. Additionally, the system utilizes a Cascaded Adaptive Neuro-Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) controller to ensure that the PV array operates at its maximum efficiency under all conditions, thereby maximizing energy harvest. To continue high power quality and ensure grid compliance, the system incorporates a DQ based Artificial Neural Network (ANN) controller. The system validation is carried out using MATLAB, with results demonstrating superior performance in terms of 96.42% converter efficiency and 1.23% Total Hormonic Distortion (THD). This innovative approach not only improves the overall efficiency and reliability but also ensures that it meets the requirements of modern grids.https://eej.aut.ac.ir/article_5908_8804f94e16ba5b680e239a554a08f7d2.pdfAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-291058120260101Hybrid Energy System for EV Charging Station Using PV Fed Z-Source Modified Luo Converter and Fuel Cell Integration205224590910.22060/eej.2025.24379.5697ENBolluPrabhakarDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India. Rajahmundry0009-0005-9237-2008DondapatiraviRavi KishoreDepartment of Electrical and Electronics Engineering, Godavari Global University, Rajahmundry, India.0000-0002-2567-2888Uday KumarUpputuriDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India.Sunkara SatyaSureshDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India.VallbhuniGovindDepartment of Electrical and Electronics Engineering, Godavari Institute of Engineering and Technology (A), Rajahmundry, India.Journal Article20250710Petroleum-based vehicles are rapidly being phased out of transportation sector as number of Electric Vehicles (EVs) rises. Nonetheless, timely and well-coordinated growth of EV Charging Stations (CSs) are crucial for quick implementation of EVs. Since randomly distributed Photovoltaic (PV) system causes high power losses and voltage variances that exceed permitted limitations, integrating EVCSs into the current distribution network is difficult. This research proposes an EV charging solution supported by PV systems and fuel cells (FC) to sustain a variable load under an optimized energy management strategy. To overcome the intermittent nature of PV system, a Z-source modified Luo converter is employed, which provides higher efficiency and voltage gain. A Walrus optimized Proportional Integral (PI) controller is utilized to improve performance of developed converter with stabilized voltage. The performance of developed FC system is improved by using Boost converter with PI controller. In order to meet load requirement of the grid-connected charging station during unavailability of PV or FC shutdown condition, the grid source power the EV, thus ensures effective EV charging even under uncertain environmental conditions. The developed work is verified through MATLAB/Simulink and outcomes reveal higher converter efficieny of 97.14% with improved voltage gain, offering uninterrupted power supply to EVs.https://eej.aut.ac.ir/article_5909_9b16759a62899465ab21e2e79d2ef75c.pdf