Original Research Paper
Electrical Machines
Seyede Delaram Sadr; Hamid Reza Izadfar
Abstract
Background and Objectives:Linear Synchronous Motors (LSMs) provide high precision, fast response, and reduced mechanical complexity, making them attractive for applications such as transportation, automation, robotics, and medical systems. Although numerous studies have investigated their structures, ...
Read More
Background and Objectives:Linear Synchronous Motors (LSMs) provide high precision, fast response, and reduced mechanical complexity, making them attractive for applications such as transportation, automation, robotics, and medical systems. Although numerous studies have investigated their structures, modeling, and optimization, challenges such as end effects, thermal management, and cost reduction remain unresolved. This review aims to synthesize recent advancements and highlight future directions for LSM design and optimization.Methods: The study systematically reviews 54 high-quality research papers covering structural configurations, electromagnetic and thermal modeling approaches, optimization techniques, and application domains of LSMs. Comparative analysis includes flat, tubular, coreless, and superconducting designs, along with analytical, magnetic equivalent circuit (MEC), and finite element method (FEM) modeling. Multi-objective optimization strategies, intelligent algorithms, and material innovations such as Halbach arrays and grain-oriented steels are also examined.Results: Recent research demonstrates that transverse flux and tubular structures enhance thrust density by 20–35% and up to 25%, respectively, while coreless and superconducting designs reduce cogging and enable threefold thrust improvements. Advanced FEM-based multiphysics modeling provides accurate prediction of coupled electromagnetic, thermal, and mechanical behavior. Optimization strategies based on evolutionary algorithms achieved up to 12.5% thrust improvement, 8.7% loss reduction, and significant thermal enhancements through innovative cooling designs. Conclusion: LSMs are advancing through structural innovations and intelligent optimization. Despite recent progress, challenges such as cooling, scalability, and material costs persist. Future developments will rely on adaptive control, machine-learning- based design, and novel materials, strengthening the role of LSMs in industry and emerging technologies.
Original Research Paper
Artificial Intelligence
Amir Mahdi Sedghi; Shahla Nemati
Abstract
Background and Objectives: Brain tumor detection in MRI images is critical for early diagnosis and effective treatment, yet manual interpretation is time-consuming and prone to variability. Deep learning models such as YOLO have advanced real-time object detection, but their speed–accuracy tradeoff ...
Read More
Background and Objectives: Brain tumor detection in MRI images is critical for early diagnosis and effective treatment, yet manual interpretation is time-consuming and prone to variability. Deep learning models such as YOLO have advanced real-time object detection, but their speed–accuracy tradeoff remains a challenge for medical tasks involving small or low-contrast lesions. The potential of transformer-based detectors like RT-DETR to simultaneously improve accuracy and maintain real-time speed in clinical settings is not well established.Methods: This study performed a controlled head-to-head comparison between the proposed model (RT-DETR-L-based model) and the YOLOv8s models using a curated, single-class brain tumor MRI dataset of 300 images. Both models were trained and evaluated under identical conditions with comprehensive data augmentation strategies, and their performance was assessed using standard object detection metrics including precision, recall, specificity, and mean Average Precision (mAP) across multiple IoU thresholds.Results: The proposed model achieved higher localization fidelity and overall accuracy compared to YOLOv8s, with mAP@0.5:0.95 of 0.493 versus 0.421 and mAP@0.5 of 0.963 versus 0.941. Precision and specificity for the proposed model reached 1.000, eliminating false positives, while recall was slightly lower than YOLOv8s (0.925 vs. 0.932), indicating a marginal increase in missed detections. Qualitative analysis confirmed robust detection across various tumor sizes and intensities, though some small or low-contrast lesions were missed.Conclusion: Proposed model surpasses YOLOv8s in accuracy and specificity for real-time brain tumor detection in MRI images, offering a promising balance between speed and precision. However, its slightly lower recall underscores the need for further refinement to minimize false negatives. The findings suggest transformer-based detectors can narrow the speed–accuracy gap in medical imaging, but broader validation and optimization for resource-constrained environments are required for clinical deployment. Future work should focus on enhancing sensitivity and generalizability through advanced augmentation, larger datasets, and ensemble approaches.
Original Research Paper
Wireless Communications
Mojtaba Hajiabadi; Naaser Neda; Amir Moradband Toroghi
Abstract
Background and Objectives: This research addresses the issue of channel estimation and beamforming in systems with Reconfigurable Intelligent Surface (RIS). RIS is able to significantly improve coverage by controlling the phase and amplitude of the reflected signals through nearly passive elements. This ...
Read More
Background and Objectives: This research addresses the issue of channel estimation and beamforming in systems with Reconfigurable Intelligent Surface (RIS). RIS is able to significantly improve coverage by controlling the phase and amplitude of the reflected signals through nearly passive elements. This advantage is highly dependent on the availability of accurate channel state information (CSI), which is difficult to obtain, and even more so in realistic scenarios where the RIS phase variations are limited to a small number of discrete surfaces due to hardware limitations.Methods: To study this issue, we propose a new CSI estimation paradigm called recursive averaging, which extends the traditional least squares (LS) estimator but compensates for its weaknesses under low SNR and quantized phase regimes, known as (RALS). The new approach involves combining a recursive update scheme that sequentially improves the CSI estimates through recursive averaging and an adaptive feedback framework. This provides better robustness against noise and quantization-induced distortion, and allows for more precise RIS configuration under the hardware constraints of a non-ideal system. The aim is to reduce the channel estimation error and reduce the bit error rate (BER) by considering the practical implementation of the method. In addition, this study also investigates the effect of discrete phase.Results: We analyze the performance of RALS under idealized continuous-phase and discrete-phase scenarios, where the phase of each RIS element is quantized with a finite number of bits. Simulation results show that RALS outperforms traditional LS and other reference estimators measured in MSD and BER, especially in situations where the number of quantized bits is low or the SNR is poor.Conclusion: Simulation results show that the proposed method provides higher accuracy channel estimation with less estimation error. Integrating accurate channel estimation with efficient beamforming strategy, overall system performance is significantly enhanced. More specifically, it is shown through simulations that 4-bit resolution is sufficient for phase discretization considering real reflection phase constraints. Interestingly, the devised approach achieves such improved performance without engaging in huge computational complexity, thus being feasible to implement in real-time in RIS-based systems.
Original Research Paper
Image Annotation and Retrieval
Sajad Mohamadzadeh; Mohammad Gharehbagh
Abstract
Background and Objectives: Content-Based Image Retrieval (CBIR) systems are crucial for managing the exponential growth of digital imagery. Traditional methods relying on handcrafted features often fail to scale and capture semantic content. Although deep learning enhances retrieval quality, challenges ...
Read More
Background and Objectives: Content-Based Image Retrieval (CBIR) systems are crucial for managing the exponential growth of digital imagery. Traditional methods relying on handcrafted features often fail to scale and capture semantic content. Although deep learning enhances retrieval quality, challenges persist in computational complexity and efficiency. This paper introduces a hybrid CBIR framework that combines unsupervised deep feature learning, adaptive hashing, and VP-Tree-based hierarchical search optimization. The proposed system, evaluated on CIFAR-10, ImageNet subset, and a custom medical imaging dataset, achieves a mean average precision (mAP) of 96.1% and reduces retrieval latency by approximately 40% compared to conventional methods. By leveraging autoencoder-driven latent feature extraction and scalable metric space partitioning, our framework demonstrates superior performance in scalability, retrieval speed, and accuracy for large-scale applications.Methods: The proposed framework employs autoencoder-driven latent space encoding to extract compact yet semantically rich feature representations, ensuring robust discriminability across diverse image categories. To enhance retrieval efficiency, a hybrid search mechanism is implemented: a Euclidean-based nearest neighbor scheme O(N log N) is used for moderate-scale datasets, while a VP-Tree-based hashing scheme O(log N) is applied for large-scale retrieval scenarios. By leveraging hierarchical metric space partitioning, the method significantly reduces search complexity while maintaining retrieval accuracy.Results: Extensive evaluations show the proposed framework outperforms traditional and modern deep hashing techniques, achieving higher mean average precision, lower search latency, and better storage efficiency for both moderate and large-scale datasets. By integrating unsupervised representation learning, advanced hashing, and optimized search structures, the system surpasses conventional methods in speed and precision.Conclusion: This study presents a highly scalable and computationally efficient CBIR framework that addresses the limitations of existing methods by combining unsupervised deep feature learning, adaptive hashing, and hierarchical search structures. The results highlight the framework's ability to achieving high retrieval accuracy and efficiency, thus making it suitable for real-time applications in large-scale multimedia repositories.
Original Research Paper
Graph Clustering
Mohammad Asadpour; Shahin Pourbahrami
Abstract
Background and Objectives: One of the most important clustering methods is density-based clustering. This technique operates on the idea that clusters are regions of higher data density, separated by areas of lower density. Density Peak Clustering (DPC) is a modern density-based algorithm designed to ...
Read More
Background and Objectives: One of the most important clustering methods is density-based clustering. This technique operates on the idea that clusters are regions of higher data density, separated by areas of lower density. Density Peak Clustering (DPC) is a modern density-based algorithm designed to efficiently identify cluster centers by constructing a decision graph. In this graph, points with high local density and a large distance from other high-density points are selected as cluster centers. Once these centers are determined, the remaining non-central points are assigned to clusters based on their proximity to the nearest center. However, DPC performs poorly on manifold datasets with varying densities and is highly sensitive to the selection of the cut-off distance parameter. Methods: To address these limitations and improve clustering performance, this study introduces an approach that employs the radial distribution function to quantify the relationship between data points and high-density regions. This method enables the estimation of the probability of finding neighboring points around a central or dense point, and a histogram is generated to represent these relationships. Results: Unlike traditional DPC, the proposed method eliminates the need for a distance cut-off parameter. The approach was implemented using the natural neighbor algorithm and the radial distribution function in a MATLAB environment. Conclusion: Experimental results demonstrated significant improvements in clustering accuracy and reductions in execution time compared to existing methods.
Original Research Paper
Artificial Intelligence
Ali Bazghandi
Abstract
Background and Objectives: Random number generation is essential in simulation, cryptography, and statistical modeling. Classical PRNGs such as the Linear Congruential Generator and Mersenne Twister are efficient but exhibit predictability and correlation. Newer families like PCG and BRG improve statistical ...
Read More
Background and Objectives: Random number generation is essential in simulation, cryptography, and statistical modeling. Classical PRNGs such as the Linear Congruential Generator and Mersenne Twister are efficient but exhibit predictability and correlation. Newer families like PCG and BRG improve statistical balance yet remain static after initialization, while chaotic and neural methods face reproducibility and stability issues. To overcome these limits, we propose the Adaptive Multi-Layer Random Generator (AMLRG), designed to deliver self-regulating pseudorandomness through adaptive feedback and hybrid entropy sources.Methods: AMLRG combines three layers: (i) an index generator based on linear, logistic, or chaotic processes, (ii) a uniform distribution module, and (iii) an adaptive feedback system that tunes parameters in real time. Online diagnostics—Kolmogorov–Smirnov tests, autocorrelation analysis, and Shannon entropy—direct dynamic adjustment. Implemented in Python, the system produces binary streams and diagnostic plots. Evaluation involved ablation studies (removing feedback, switching, or stratification), comparison with LCG, PCG, BRG, and logistic-only baselines, and validation using Dieharder, TestU01, and NIST SP 800-22.Results: AMLRG produced lower KS distances, near-zero autocorrelation, and entropy close to theoretical maxima, outperforming all baselines. Ablation confirmed the contribution of each layer to statistical quality. Results show stable behavior across 200,000 values, with speed comparable to PCG but greater adaptability.Conclusion: AMLRG introduces dynamic correction that improves independence and uniformity in pseudorandom sequences. Its layered architecture suits engineering simulations, adaptive systems, and security-sensitive statistical preprocessing. Future work will target non-uniform distributions, GPU acceleration, and hardware implementation.
Original Research Paper
Data Mining
Fatemeh Akbari; Eynollah Khanjari
Abstract
Background and Objectives: So far, several methods have been proposed to detect communities, which indicate the high importance of discovering communities for understanding social networks and detecting useful and hidden patterns in the network. The goal of such analyses is to find a group of users with ...
Read More
Background and Objectives: So far, several methods have been proposed to detect communities, which indicate the high importance of discovering communities for understanding social networks and detecting useful and hidden patterns in the network. The goal of such analyses is to find a group of users with common characteristics. Basically, social networks are considered as graphs, so the analysis is also done using graph methods, in which nodes represent individuals and edges represent relationships between them. Since community detection is an NP-complete problem, several meta-heuristic approaches have been used to tackle this problem, mainly considering "modularity" as the objective function. In most approaches, modularity has been used, which suffers from the limitation of resolution and cannot detect communities that are small in size and consider it in combination with large communities.Methods: In this paper, a new hybrid algorithm of bee colony and genetics is proposed for community detection which performs optimization using the "balanced modularity" fitness function. In this algorithm, parallel processing is used to speed up optimization, genetic algorithm is used to create the initial population, and genetic operators are used in the search by bees.Results: Experiments on well-known real-world networks, including karate, American football, dolphins, and political books, have shown that our method provides more accurate results than the state-of-the-art community detection methods.Conclusion: The combined optimization of bee colony and genetics not only provides globally optimal solution but also it does not need prior information about the number as well as the structure of communities.
Original Research Paper
Image Processing
Morteza Akbari; Seyyed Mohammad Razavi; Sajad Mohamadzadeh
Abstract
Background and Objectives: Multi-object tracking in dense, multi-camera environments remains challenging due to occlusions, lighting variations, and fragmented trajectories. While existing methods rely on hierarchical two-step approaches or complex Bayesian filters, they often fail to fully exploit spatio-temporal ...
Read More
Background and Objectives: Multi-object tracking in dense, multi-camera environments remains challenging due to occlusions, lighting variations, and fragmented trajectories. While existing methods rely on hierarchical two-step approaches or complex Bayesian filters, they often fail to fully exploit spatio-temporal correlations or to approach global consistency across cameras and frames. This study aims to address these limitations by proposing a novel graph-based deep learning model for continuous person tracking that independently optimizes spatial and temporal associations.Methods: The proposed model decomposes multi-camera tracking into two tasks: temporal association (linking objects across frames using velocity and time) and spatial association (aligning objects from multiple viewpoints). A spatio-temporal graph structure is constructed, with nodes representing detected objects and edges encoding relationships. Message Passing Networks (MPNs) iteratively update node and edge features, while a graph consensus fusion module merges spatial and temporal graphs for robust tracking. The model is trained using Focal Loss and evaluated on the Wildtrack and CAMPUS datasets.Results: The model achieves state-of-the-art performance, with a MOTA score of 85.5% on Wildtrack and 77.4–87.4% on CAMPUS subsets. Key improvements include a 100% MT (mostly tracked) rate and 0% ML (mostly lost) rate on CAMPUS, demonstrating exceptional robustness in occluded and crowded scenes. The IDF1 score (87.2%) highlights superior identity preservation. The decoupled design reduces graph size, which improves scalability.Conclusion: By decoupling spatial and temporal associations and leveraging graph-based optimization, the proposed model significantly enhances tracking accuracy and reliability in multi-camera settings. This work provides a framework for applications like surveillance and autonomous systems, with future potential for attention mechanisms and adaptive graph integration.
Original Research Paper
Arash Kosari
Abstract
Background and Objectives: Quantum Key Distribution (QKD) ensures secure communication through quantum mechanics, but real-world implementations face vulnerabilities from detector blinding, time-shift, and side-channel attacks. While Measurement-Device-Independent QKD (MDI-QKD) mitigates detector vulnerabilities, ...
Read More
Background and Objectives: Quantum Key Distribution (QKD) ensures secure communication through quantum mechanics, but real-world implementations face vulnerabilities from detector blinding, time-shift, and side-channel attacks. While Measurement-Device-Independent QKD (MDI-QKD) mitigates detector vulnerabilities, it lacks real-time attack monitoring and struggles with finite-key limitations. This study presents an MDI ack QKD protocol that integrates deterministic acknowledgment pulses and multi-intensity decoy states to achieve robust, device-independent security with real-time attack detection.Methods: The proposed protocol combines MDI-QKD’s device-independent framework with interleaved deterministic acknowledgment pulses and four-level decoy intensities. Alice and Bob generate weak coherent pulses with randomized phases, embedding acknowledgment pulses with probability ( Pd = 0.1 ) to probe channel integrity. An untrusted relay performs Bell-state measurements using superconducting nanowire single-photon detectors (SNSPDs). Multi-intensity decoy statistics enable finite-key parameter estimation, while integrated photonic platforms ensure scalability. Security is analyzed using the universally composable framework, with simulations and preliminary experiments conducted over metropolitan fiber distances.Results: Numerical simulations demonstrate secure key rates exceeding 10 Mbps at 50 km and ~1 Mbps at 100 km under realistic conditions (0.2 dB/km fiber loss, 85% detector efficiency, 1 GHz pulse rate). Experimental tests on an integrated photonic chip at 1550 nm achieved raw key rates of 1.1 Mbps at 50 km with decoy accuracy within ±7%. Deterministic acknowledgments detected blinding attacks with high sensitivity, and multi-intensity decoys provided tight finite-key bounds, maintaining composable security against collective and coherent attacks.Conclusion: The MDI ack QKD protocol achieves high-rate, device-independent quantum key distribution with real-time attack monitoring, offering a scalable solution for metropolitan quantum networks. Its compatibility with integrated photonics enables compact, stable implementations, while deterministic acknowledgments and multi-intensity decoys ensure robust security against evolving threats. This approach paves the way for practical, unconditionally secure communication systems, with potential for satellite-ground and multi-node network extensions.
Original Research Paper
Analogue Integrated Circuits
Atousa Gholami Boorkheyli; Majid Babaeinik; Hadi Dehbovid; Vahid Ghods
Abstract
Background and Objectives: This research aims to optimize component placement in integrated systems using evolutionary algorithms. The primary goal is to generate a compact floorplan while satisfying design constraints, particularly in analog circuits where symmetry and proximity constraints are critical ...
Read More
Background and Objectives: This research aims to optimize component placement in integrated systems using evolutionary algorithms. The primary goal is to generate a compact floorplan while satisfying design constraints, particularly in analog circuits where symmetry and proximity constraints are critical to minimizing coupling interference and enhancing performance. The study proposes using a convolutional neural network (CNN) to extract these placement constraints, with its parameters optimized via the non-dominated sorting genetic algorithm III (NSGA-III). Additionally, a hybrid routing approach combining simulated annealing (SA) and NSGA-III is introduced to improve routing efficiency through multi-objective optimization.Methods: The placement constraints, including symmetry and proximity requirements, are extracted using a CNN, whose parameters are optimized by NSGA-III. For routing, a hybrid approach is employed where SA generates initial routing solutions, which are then refined by NSGA-III for multi-objective optimization. The proposed method is implemented on a two-stage recycling folded cascade (RFC) amplifier in 0.18μm CMOS technology with a 1.8V supply voltage. A dedicated MATLAB toolbox is developed to facilitate placement while adhering to design rules using optimization algorithms.Results: Simulation results confirm the effectiveness of the proposed methodology, demonstrating optimized placement and routing with improved circuit performance. The combination of CNN and NSGA-III successfully generates a compact and efficient layout, while the hybrid routing approach (SA + NSGA-III) enhances the routing process. The RFC amplifier case study shows better utilization of physical resources and performance improvements, validating the method's efficiency.Conclusion: This study demonstrates that the proposed method, integrating evolutionary algorithms and CNN, effectively optimizes placement and routing in integrated systems. The CNN-based constraint extraction and NSGA-III optimization enable compact layouts, while the hybrid routing approach improves multi-objective optimization. Simulations on the RFC amplifier confirm enhanced circuit performance and resource utilization. This method offers significant advantages over traditional approaches and is applicable to complex and industrial designs.
Original Research Paper
Deep Learning
Reyhaneh Bagheri; Fatemeh Tabib Mahmoudi; AmirHossein Gholamian
Abstract
Background and Objectives: Accurate soil moisture estimation is essential for various hydrological processes such as irrigation planning, and environmental monitoring; however, prediction accuracy is often limited by sparse in-situ measurements and uncertainties in remote sensing products. This study ...
Read More
Background and Objectives: Accurate soil moisture estimation is essential for various hydrological processes such as irrigation planning, and environmental monitoring; however, prediction accuracy is often limited by sparse in-situ measurements and uncertainties in remote sensing products. This study aims to develop an enhanced soil moisture prediction framework by integrating a Gated Recurrent Unit (GRU) deep learning model with multi source data augmentation techniques in order to evaluate its performance across diverse climatic conditions. Methods: This study proposed an enhanced GRU deep learning framework supported by multi source data augmentation to predict soil moisture across ten U.S. Climate Reference Network (USCRN) stations representing diverse climatic and ecological conditions. The proposed model integrates Conv1D layers, bidirectional GRUs, multi-head attention, and dense layers to capture short and long-term temporal dependencies while fusing multi source inputs including ISMN in-situ measurements, SMAP products, and GLDAS. Data augmentation strategies composed of noise injection, temporal warping, scaling, and window slicing were applied to expand the training dataset and reduce overfitting. Model performance was compared against a standard GRU using some of the evaluation metrics. Results: Results demonstrate that the augmented GRU model consistently outperformed the standard GRU across all stations, with notable improvements in R² (up to 0.912), RMSE, and MAE. Performance gains were particularly evident in humid continental and Mediterranean climates, while regions with complex forested or semi-arid environments also benefited from data augmentation. These improvements confirm that data augmentation enhances the model’s generalization under climatic variability and mitigates limitations associated with SMAP resolution and GLDAS uncertainty.Conclusion: The integration of multi-source datasets with an augmented GRU architecture provides a reliable framework for soil moisture estimation across diverse environments. The proposed approach offers strong potential for applications in environmental monitoring, precision agriculture, and water resource management.
Original Research Paper
Computer Vision
Vincent Andrew Akpan; David Ayo-oluwa Adegoke; Ebunoluwa Temiloluwa Adejayan; Kehinde Adesola Adepoju
Abstract
Background and Objectives: The manual method of writing down vehicle plate numbers (VPNs), vehicle types, date, and time-stamps at the point of entry into and/or exit from the premises of organizations as well as the exit and/or entry time are not only time-consuming and stressful but are also prone ...
Read More
Background and Objectives: The manual method of writing down vehicle plate numbers (VPNs), vehicle types, date, and time-stamps at the point of entry into and/or exit from the premises of organizations as well as the exit and/or entry time are not only time-consuming and stressful but are also prone to errors, delays, inconsistency and possible loss of hand-written data due to possible environmental hazards which makes this archaic method unreliable especially for security reasons. This study presents an artificial intelligence-based YOLOv3 using DarkNet-53 deep convolutional neural network (CNN) model architecture for the development of an automatic vehicle inventory system (AVIS) with a PostgreSQL-based dynamic relational database system (RDBS) for captured data storage and retrieval in real-time using Google cloud storage/retrieval.Methods: The AVIS with dynamic RDBS employs power-over-Ethernet (PoE) switch, PoE IP-based camera, Airtel router/Wi-Fi module and YOLOv3 using DarkNet-53 algorithm to capture and process VPNs from streaming video of moving vehicles. The processed results are stored in a properly designed dynamic RDBS over Google cloud storage system. The dynamic RDBS automatically creates and inserts all relevant vehicle information for security surveillance and tracking purposes. Several standard quantitative and qualitative metrics have been used to evaluate the performances of the YOLOv3 using DarkNet-53 architecture against YOLOv8 using CSPDarkNet-53 and YOLOv3 using SqueezeNet model architectures for comparison purposes.Results: Quantitatively, the YOLOv3 using DarkNet-53 and YOLOv8 using CSPDarkNet-53 achieved virtually equal performance metrics except for the excessive long execution time of 4.5839 hours used by YOLOv8 with CSPDarkNet-53compared to the 2.9713 minutes used by the YOLOv3 with DarkNet-53. The YOLOv3 with SqueezeNet used only 1.9901 minutes with relatively lower performance metric values. Qualitatively, successful and accurate LPNs detection and recognition with dynamic RDBS update to the cloud within 3 seconds for 25 random vehicles entering and/or exiting the premises of a car dealer company for a period of three days between 10:00am and 2:00pm daily has been achieved with YOLOv3 using DarkNet-53 model architecture.Conclusion: The proposed low-cost AVIS based on YOLOv3 using DarkNet-53 model architecture with a PostgreSQL dynamic RDBS and Google cloud storage have been successfully designed, implemented and validated with successful results for LPN detection and recognition. The proposed techniques offers promising potentials for timely and accurate data collection to optimize vehicle inventory management, control and operations for security surveillance design.
Original Research Paper
Electrical Machines
Alireza Shams; Esmaeel Rokrok; Behrooz Rezaeealam; Abbas-Ali Zamani
Abstract
Background and Objectives: Interior permanent magnet synchronous machines (IPMSMs) have gained increasing attention in electric vehicle applications due to their high power density, desirable efficiency, and capability of delivering maximum torque over a wide speed range. Despite these advantages, challenges ...
Read More
Background and Objectives: Interior permanent magnet synchronous machines (IPMSMs) have gained increasing attention in electric vehicle applications due to their high power density, desirable efficiency, and capability of delivering maximum torque over a wide speed range. Despite these advantages, challenges such as torque ripple and suboptimal efficiency remain. This study aims to propose a design and multi-objective optimization approach for Stator-Optimized Delta-Type IPMSM (SO-DT-IPMSM) motor to enhance efficiency, reduce torque ripple, and improve average torque. Methods: A multi-objective particle swarm optimization (MOPSO) was employed to determine the optimal set of stator parameters. In this study, an existing delta-type IPMSM rotor topology was adopted and all rotor parameters were kept fixed, while the optimization was exclusively performed on stator geometry. Electromagnetic modeling and performance evaluation of the proposed design were carried out using Ansys Electronics. Following the optimization process, a prototype motor was manufactured and assembled based on the optimized design parameters, and experimental tests were conducted to validate the simulation results. Results: Simulation results revealed significant improvements in the SO-DT-IPMSM compared with the Nissan Leaf IPMSM motor (Initial IPMSM). The optimized design achieved a 21% increase in average torque, 40% reduction in torque ripple, and 5% improvement in overall efficiency. Experimental tests performed on the fabricated prototype confirmed the accuracy of the simulation findings and demonstrated strong agreement between analytical and experimental data.Conclusion: The proposed design and optimization approach effectively enhanced torque, torque ripple, and efficiency in the IPMSM. Beyond the validated experimental performance, the results demonstrate that the presented methodology can serve as a practical solution for improving electric vehicle motor performance. Moreover, the introduced optimization framework has the potential to be extended to other motor topologies and applications.
Original Research Paper
Artificial Intelligence
Mujtaba Sultani; Negin Daneshpour
Abstract
Background and Objectives: Discussion forums in Massive Open Online Courses (MOOCs) enable students to interact with instructors and share educational concerns. However, identifying urgent posts within the vast volume of discussions poses significant challenges. High dropout rates and the need for timely ...
Read More
Background and Objectives: Discussion forums in Massive Open Online Courses (MOOCs) enable students to interact with instructors and share educational concerns. However, identifying urgent posts within the vast volume of discussions poses significant challenges. High dropout rates and the need for timely responses to urgent queries highlight the importance of efficient classification systems. This study addresses the binary classification of student posts in the Stanford MOOC Posts dataset into urgent and non-urgent categories, and aims to improve performance in the presence of class imbalance.Methods: We propose a hybrid deep learning model that integrates BERT-based contextual embeddings with a Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) architecture to capture both local textual features and long-term dependencies. To mitigate the class imbalance issue, BERT-based data augmentation technique was employed which enriches minority class samples, and enhance model generalization and urgent post detection. The model’s performance was compared against baseline methods, including CNN, LSTM, BiLSTM, and other state-of-the-art models. Evaluation metrics such as F1-weighted score and class-specific F1 scores were used to assess effectiveness.Results: The model achieved a 93.3% F1-weighted score and an 84.1% F1 score for the urgent class which surpasses the best-performing state-of-the-art model by 0.6% and 0.8%, respectively. The results show the effectiveness of augmentation and hybrid architecture while identifying urgent posts, particularly within imbalanced datasets.Conclusion: This research introduces a scalable and effective framework for urgent post detection in MOOCs. By leveraging BERT-based augmentation and a CNN–BiLSTM hybrid architecture that integrates contextual and sequential learning, the study provides automated forum analysis, offer timely insights for instructors and course designers to enhance students support, engagement, and retention.
Original Research Paper
Image Processing
Fatemeh Jafari; Hamidreza Ghafari; Hassan Farsi
Abstract
Background and Objectives: Breast cancer is a leading cause of mortality among women worldwide. Early detection plays a pivotal role in reducing mortality rates and improving patient outcomes by identifying risk factors, enhancing screening methods, and enabling timely treatment. Recent advances in artificial ...
Read More
Background and Objectives: Breast cancer is a leading cause of mortality among women worldwide. Early detection plays a pivotal role in reducing mortality rates and improving patient outcomes by identifying risk factors, enhancing screening methods, and enabling timely treatment. Recent advances in artificial intelligence (AI) and deep learning have facilitated accurate and efficient analysis of medical images, supporting rapid and precise breast cancer detection. This study aims to develop a fast and reliable approach for detecting breast cancer masses in mammography images using a deep learning framework.Methods: The proposed approach employs a Faster R-CNN architecture with a ResNet backbone for robust feature extraction. Fuzzy logic is integrated to adaptively adjust the learning rate, improving training stability. Transfer learning and data augmentation techniques are applied to enhance model generalization and reduce overfitting. The method labels affected regions in mammography images, enabling accurate localization of cancerous areas.Results: Experiments were carried out using the CBIS-DDSM dataset. The proposed model demonstrated a cancer detection accuracy of 97.84%, an Intersection over Union (IoU) of 98.12%, and a mAP50 of 0.83, highlighting its exceptional performance in accurately localizing breast cancer masses.Conclusion: The integration of Faster R-CNN with ResNet, fuzzy logic-based learning rate adaptation, transfer learning, and data augmentation yields a highly effective solution for automated breast cancer detection. The results highlight the potential of this method to improve early diagnosis and support clinical decision-making in breast cancer screening.
Original Research Paper
Artificial Intelligence
Motahareh Akbari Poodineh; Fatemeh Zare Mehrjardi; Mohsen Sardari Zarchi
Abstract
Background and Objectives: Cardiovascular diseases, particularly cardiac arrhythmias, are among the leading causes of mortality worldwide. Early and accurate diagnosis is essential for improving patient outcomes. Although electrocardiogram (ECG) signals are widely used for arrhythmia detection, manual ...
Read More
Background and Objectives: Cardiovascular diseases, particularly cardiac arrhythmias, are among the leading causes of mortality worldwide. Early and accurate diagnosis is essential for improving patient outcomes. Although electrocardiogram (ECG) signals are widely used for arrhythmia detection, manual interpretation remains time consuming and error prone. Therefore, this study proposes an innovative, optimized two stage deep learning framework for the reliable diagnosis of cardiac arrhythmias from ECG signals, aiming to enhance both accuracy and robustness.Methods: The key innovation lies in the first stage, where the autoencoder’s reconstruction error threshold is optimized using a Genetic Algorithm (GA) to maximize the separation between normal and abnormal signals. Only signals identified as abnormal proceed to the second stage, a Convolutional Neural Network (CNN) that classifies them into four arrhythmia types (Supraventricular, Ventricular, Fusion, and Unknown beats). All experiments were conducted on the MIT BIH Arrhythmia Database using a stratified split, with SMOTE applied exclusively to the CNN training set to address class imbalance. Performance was evaluated through 5 fold cross validation.Results: The proposed AE GA CNN+SMOTE framework achieved an average accuracy of 97.89 ± 0.25%, precision of 97.90 ± 0.24%, recall of 97.68 ± 0.29%, and an F1 score of 97.69 ± 0.28%. It outperformed the single stage CNN+SMOTE baseline by +6.28% in accuracy (p < 0.001) and showed statistically significant improvements over all other two stage variants (p < 0.05).Conclusion: The two stage architecture, enhanced by GA driven threshold optimization and SMOTE balancing, demonstrates high accuracy and robustness for automated arrhythmia screening. The statistically validated performance gains support its potential as a decision support tool for clinical and real time ECG analysis.
Original Research Paper
Electrical Machines
Seyed Reza Mousavi-aghdam; Seyed Abbas Azimi; Farzad Sedaghati
Abstract
Background and Objectives: Synchronous reluctance motors (SynRMs) have considered as energy-efficient alternatives to conventional induction motors (IMs), primarily due to high efficiency. Despite their low losses, SynRMs are hindered by inadequate line-start capability and a low power factor, which ...
Read More
Background and Objectives: Synchronous reluctance motors (SynRMs) have considered as energy-efficient alternatives to conventional induction motors (IMs), primarily due to high efficiency. Despite their low losses, SynRMs are hindered by inadequate line-start capability and a low power factor, which restrict their use in industrial settings. This article addresses these limitations by introducing a line-start permanent magnet-assisted SynRM (LS-PMaSynRM) that incorporates fluid-type flux barriers. This design aims to enhance starting performance and increasing power factor.Methods: The design process entailed a parametric sensitivity analysis of critical motor characteristics, including rotor geometry, stator winding configuration, and stator slot count. Finite Element Method (FEM) simulations were executed using time-stepping analysis to assess the motor's electromagnetic behavior under both transient and steady-state conditions. Performance metrics such as torque ripple, average torque, efficiency, and power factor were evaluated. Comparative simulations with conventional SynRM and PMaSynRM designs were also conducted to benchmark improvements.Results: The proposed LS-PMaSynRM exhibited substantial enhancements in line-start capability, achieving stable synchronization within a brief period. The motor demonstrated a significant increase in power factor relative to conventional SynRM designs, while maintaining high efficiency throughout the operating range.Conclusion: The study presents an LS-PMaSynRM architecture that effectively addresses traditional limitations in line-start performance and power factor. These findings support the broader industrial adoption of SynRMs and offer a practical design pathway for future high-efficiency motor applications.
Original Research Paper
Electrical Machines
Pouria Nadri; Behrooz Rezaeealam; Morteza Mikhak-Beyranvand
Abstract
Background and Objectives: Dual-rotor synchronous motors with counter-rotation are of significant interest for electric machine design due to their high performance and specific applications. In this study, a new Counter-Rotating Dual-Rotor Synchronous Motor (CRDRSM) is presented, with the permanent ...
Read More
Background and Objectives: Dual-rotor synchronous motors with counter-rotation are of significant interest for electric machine design due to their high performance and specific applications. In this study, a new Counter-Rotating Dual-Rotor Synchronous Motor (CRDRSM) is presented, with the permanent magnet (PM) rotor as the outer rotor and the reluctance rotor as the inner rotor.Methods: To identify the optimal structure, the effects of distributed and fractional-pitch windings are first compared. Then, various PM and reluctance rotor topologies are examined in order to select the optimal combination. Despite high output torque, cogging torque significantly affects motor performance; therefore, reducing cogging torque is the main concern of this research. Dimensional optimization is conducted using the Taguchi method to minimize cogging torque in the PM rotor. Four key design parameters, including the PM arc, PM thickness, stator opening slot, and stator tooth width, are selected as optimization variables, while other parameters are kept constant. The minimum and maximum ranges of these variables are determined using parametric scanning and ANSYS Maxwell finite element software. Briefly, the optimization process proceeds in three stages: (1) winding configuration comparison, (2) selection of optimal inner and outer rotor structures, and (3) dimensional optimization using the Taguchi method.Results: Analysis of the results demonstrates that the cogging torque of the proposed motor is reduced by up to 62.36%, the output power and efficiency are increased, and the voltage THD is also reduced. Other performance characteristics, including output torque and electromagnetic stability, are improved compared to the initial design or remain at a desirable level.Conclusion: Finite Element Analysis (FEA) demonstrated that the distributed winding configuration delivers the best performance among all tested options. Model C, featuring a hyperbolic-line reluctance inner rotor combined with a surface-mounted PM outer rotor, was identified as the best configuration. This model offers an excellent balance of high torque, low torque ripple, minimized back-EMF harmonics, and satisfactory efficiency, making it highly suitable for submarine propulsion systems. To further reduce cogging torque (one of the primary sources of torque ripple and acoustic noise), the motor geometry was optimized using the Taguchi method and FEA. Overall, the electromagnetic performance of the proposed CRDRSM was validated in terms of flux density distribution, output torque, and cogging torque.
Original Research Paper
Multi-Source Signal Analysis
Hamed Hakkak; Mohammad Mahdi Khalilzadeh; Mahdi Azarnoosh; Hamid Reza Kobravi
Abstract
Background and Objectives: While deep learning has significantly advanced visual content recognition, existing models primarily rely on image data alone, neglecting the rich cognitive context embedded in neural responses. This study aimed to develop and validate a novel framework that synergistically ...
Read More
Background and Objectives: While deep learning has significantly advanced visual content recognition, existing models primarily rely on image data alone, neglecting the rich cognitive context embedded in neural responses. This study aimed to develop and validate a novel framework that synergistically integrates electroencephalography (EEG) signals with visual features to achieve superior accuracy in multiclass image recognition.Methods: We designed a hierarchical attention-based deep learning architecture to fuse neural and visual information. EEG data recorded (the dataset newly developed by the authors) during visual stimulus presentation were preprocessed and analyzed using temporal models (RNN-CNN and LSTM) to extract neural features. Concurrently, visual features were extracted from the stimulus images using ResNet101 and DenseNet201 architectures. The proposed attention mechanism dynamically weighted and integrated these multimodal features, prioritizing the most salient information from each modality.Results: The proposed framework significantly outperformed conventional unimodal approaches. The hybrid RNN-CNN + ResNet101 model achieved a peak classification accuracy. A feature contribution analysis revealed that the optimal performance was attained through an integrated contribution of approximately 60% from image-derived features and 40% from EEG-derived features, demonstrating the critical complementary value of neural data.Conclusion: This study confirms that the structured, attention-based fusion of neurophysiological and visual data substantially enhances visual content recognition. The findings provide a robust and effective framework for advanced cognitive assessment applications and establish a new benchmark for multimodal integration in machine learning, highlighting the significant potential of EEG data to complement and improve computer vision tasks.
Original Research Paper
Software
Morteza Noferesti; Farzad Amiri Delouei; Sarah Aryan
Abstract
Background and Objectives: Modern operating systems struggle to manage threads with dynamic resource demands, as traditional schedulers rely on reactive heuristics that often misclassify thread behavior. This paper introduces a proactive thread classification methodology that predicts resource-bound ...
Read More
Background and Objectives: Modern operating systems struggle to manage threads with dynamic resource demands, as traditional schedulers rely on reactive heuristics that often misclassify thread behavior. This paper introduces a proactive thread classification methodology that predicts resource-bound categories by analyzing kernel event streams in real time. Methods: Our proposed five-step pipeline includes: (1) kernel event collection using LTTng, (2) system call categorization into a seven-category taxonomy covering 57 system calls, (3) PID/TID labeling based on resource usage, (4) feature extraction from the first five events, and (5) predictive modeling with multiple machine learning classifiers. Results: Our evaluation of six machine learning models, including Random Forest, LightGBM, Stacked Ensemble, MLP, CNN-BiLSTM, and BERT demonstrates that Random Forest delivers the optimal balance of high predictive performance (93.4% precision, 92.5% recall) and low inference latency (178 µs), outperforming both other ensemble methods and computationally expensive deep learning architectures. When applied to a real-world dataset [30], this optimized methodology achieves 89% precision in thread classification, which directly translates to significant system-level improvements: a 41% reduction in tail latency for interactive applications and sustained 93% CPU utilization for cpu-bound tasks.Conclusion: This paper demonstrates the efficacy of a novel, proactive thread classification methodology that accurately predicts a thread's future resource-bound category within a critically short 100 µs window from its execution start. By instrumenting a five-step pipeline, the approach successfully translates fine-grained system call sequences into predictive signatures for resource constraints, such as identifying I/O-bound threads from read/write patterns. This early detection capability provides a timely and actionable foundation for operating system schedulers to preemptively optimize thread prioritization and resource allocation, thereby enhancing overall system performance and responsiveness.
