https://jecei.sru.ac.ir/ Journal of Electrical and Computer Engineering Innovations (JECEI) en daily 1 Wed, 01 Jul 2026 00:00:00 +0330 Wed, 01 Jul 2026 00:00:00 +0330 https://jecei.sru.ac.ir/article_2319.html Background and Objectives: A Time-to-Digital Converter (TDC) is a fundamental electronic component that converts time intervals into digital representations. It plays a critical role in high-precision applications such as particle physics experiments, time-of-flight measurements, and the processing of high-frequency signals in communication systems. This paper presents a comprehensive study on the design and simulation of two innovative low-power TDC architectures.Methods: The approach introduces a novel low-power D Flip-Flop (D-FF) circuit using transmission gates (TG) and CMOS inverters to reduce power consumption while maintaining high performance. Specialized low-power delay cells are proposed for Flash TDC implementation. Detailed simulations were conducted using Cadence software with a 0.18 μm CMOS fabrication process at a supply voltage of 1.8 V.Results: The results demonstrate significant improvements in power efficiency and performance metrics, indicating the potential of the proposed TDC designs for future applications requiring precise temporal measurements. The Figure of Merit (FOM) values of the two proposed structures are 0.033 and 0.020, respectively.Conclusion: Power consumption in TDCs is a critical factor, as it directly influences the overall efficiency of electronic systems. Reducing power consumption can lead to decreased energy use, improved thermal management, and an extended lifespan for devices. Conversely, higher power consumption can generate excessive heat, which can negatively impact the system's performance and reliability. Thus, it is vital to strike an optimal balance between accuracy and power consumption in TDCs to enhance the longevity of electronic devices. This paper presents the design of delay cell circuits and a D-FF using a 0.18 µm CMOS process with a 1.8 V supply voltage. The power consumption of the proposed delay cells has been minimized through the application of the body bias technique. The performance of the delay cell has been evaluated in flash TDC circuits, and the results demonstrate the effective performance of the proposed structures. https://jecei.sru.ac.ir/article_2320.html Background and Objectives: Developing efficient task-oriented dialogue systems capable of handling multilingual interactions is a growing area of research in natural language processing (NLP). In this paper, we propose SenSimpleDS, a deep reinforcement learning-based joint task-oriented dialogue system, designed for multilingual conversations.Methods: The system utilizes a deep Q-network and the SBERT model to represent the dialogue environment. We introduce two variants, SenSimpleDS+ and SenSimpleDS-NSP, which incorporate modifications in the ε-greedy method and leverage next sequence prediction (NSP) using BERT to refine the reward function. These methods are evaluated on datasets in English, Persian, Spanish, and German, and compared with baseline methods such as SimpleDS and SCGSimpleDS.Results: Our experimental results demonstrate that the proposed methods outperform the baselines in terms of average collected rewards, requiring fewer learning steps to achieve optimal dialogue policies. Notably, the incorporation of NSP significantly improves performance by optimizing reward collection. The multilingual SenSimpleDS further showcases the system’s ability to function across languages using a random forest classifier for language detection and MPNet for environment construction. In addition to system evaluations, we introduce a new Persian dataset for task-oriented dialogue in the restaurant domain, expanding the resources available for developing dialogue systems in low-resource languages.Conclusion: SenSimpleDS, a deep reinforcement learning-based joint task-oriented dialogue system, demonstrates superior performance over baseline methods by leveraging deep Q-networks, SBERT. The integration of next sequence prediction (NSP) significantly enhances reward optimization, enabling faster convergence to optimal dialogue policies. This work establishes a foundation for future research in multilingual dialogue systems, with potential applications across diverse service domains. https://jecei.sru.ac.ir/article_2321.html Background and Objectives: To achieve zero carbon emissions, renewable energy sources have gained noteworthy regard due to their dependable performance, cost efficiency, and adaptability within systems. Increasing adoption of renewable energy sources and electric vehicle (EV) has led to a growing need for enhanced voltage boost capability. Nevertheless, most of DC sources such as solar cells have a restricted capacity for boosting power. Multilevel inverters can operate as interfaces. In this study, two topologies of switched-capacitor multilevel inverters (SC-MLI) is suggested to overcome the mentioned constraints.Methods: Each stage of the introduced SC-MLI comprises a capacitor, a DC voltage supply, a diode, and two power electronic switches. A comprehensive analysis of the operational principles, and the characteristics of the presented converter, including its charging and discharging behaviors, are provided. Furthermore, the phase-disposition pulse width modulation (PD-PWM) technique is employed to generate the output voltage waveform of the introduced multilevel SC inverter.Results: In the recommended topologies, the quantity of semiconductor power switches, isolated DC voltage supply, diodes, and so, volume and cost of the overall system are decreased in compare to similar SC-MLI topologies. The voltage across the capacitors is self-balanced accurately without using any auxiliary circuits or closed-loop systems. To validate the proposed SC-MLI's effective operation, the implemented topology's simulation and measurement results are presented. The total harmonic distortion for the 17-level inverter using the PD-PWM technique at a modulation index 1 obtained 6.97%. Conclusion: Comprehensive comparative analysis reveals that the introduced topologies have merits and superior performance compared to existing solutions regarding component number, voltage boost factor (BF), and voltage stress. Also, simulation and experimental test results verify theoretical analysis. https://jecei.sru.ac.ir/article_2347.html Background and Objectives: Facial recognition technology has become a reliable solution for access control, augmenting traditional biometric methods. It primarily focuses on two core tasks: face verification, which determines whether two images belong to the same individual, and face identification, which matches a face to a database. However, facial recognition still faces critical challenges such as variations in pose, illumination, facial expressions, image noise, and limited training samples per subject.Method: This study employs a Siamese network based on the Xception architecture within a transfer learning framework to perform one-shot face verification. The model is trained to compare image pairs rather than classify them individually, using deep feature extraction and Euclidean distance measurement, optimized through a contrastive loss function.Results: The proposed model achieves high verification accuracy on benchmark datasets, reaching 97.6% on the Labeled Faces in the Wild (LFW) dataset and 96.25% on the Olivetti Research Laboratory (ORL) dataset. These results demonstrate the model’s robustness and generalizability across datasets with diverse facial characteristics and limited training data.Conclusion: Our findings indicate that the Siamese-Xception architecture is a robust and effective approach for facial verification, particularly in low-data scenarios. This method offers a practical, scalable solution for real-world facial recognition systems, maintaining high accuracy despite data constraints. https://jecei.sru.ac.ir/article_2348.html Background and Objectives: In Natural Language Processing (NLP), sentiment analysis is crucial for understanding and extracting aspects and opinions expressed in textual data. Recent methods have emphasized determining polarity in multi-domain sentiment analysis while giving less attention to aspect and opinion extraction. Furthermore, the terms that convey aspects and opinions may have different importance in different domains, and this difference should be considered to enhance the extraction of aspect-opinion pairs. Methods: To address these challenges, we propose a Weighted Words Multi-Domain (WWMD) model for aspect-opinion pairs extraction, consisting of a self-attention mechanism and a dense network. The self-attention mechanism extracts each word's importance according to the sentence's overall meaning. The dense network is used for domain prediction. It assigns greater weight to words relevant to each domain, which leads to considering the different significance of terms across various contexts. Adding an attention mechanism to the domain module allows for a clearer understanding of different aspects and opinions across various domains. We utilize a two-channel approach, one channel extracts aspects and opinions, while the other extracts the relationships between them. The weighted words extracted by our model are simultaneously considered as the input for both channels.Results: Using weighted words specific to each domain, improves the model output.Conclusion: Evaluation results on benchmark datasets demonstrate the superiority of the proposed model compared to state-of-the-art techniques. https://jecei.sru.ac.ir/article_2349.html Background and Objectives: Unmanned Aerial Vehicles (UAVs) face significant challenges in navigating narrow passages within GPS-denied environments due to sensor and computational limitations. While deep reinforcement learning (DRL) has improved navigation, many methods rely on costly sensors like depth cameras or LiDAR. This study addresses these issues using a vision-based DRL framework with a monocular camera for autonomous UAV navigation.Methods: We propose a DRL-based navigation system utilizing Proximal Policy Optimization (PPO). The system processes a stack of grayscale monocular images to capture short-term temporal dependencies, approximating the partially observable environment. A custom reward function encourages trajectory optimization by assigning higher rewards for staying near the passage center while penalizing further distances. The navigation system is evaluated in a 3D simulation environment under a GPS-denied scenario.Results: The proposed method achieves a high success rate, surpassing 97% in challenging narrow passages. The system demonstrates superior learning efficiency and robust generalization to new configurations compared to baseline methods. Notably, using stacked frames mitigates computational overhead while maintaining policy effectiveness.Conclusion: Our vision-based DRL approach enables autonomous UAV navigation in GPS-denied environments with reduced sensor requirements, offering a cost-effective and efficient solution. The findings highlight the potential of monocular cameras paired with DRL for real-world UAV applications such as search and rescue and infrastructure inspection. Future work will extend the framework to obstacle avoidance and general trajectory planning in dynamic environments. https://jecei.sru.ac.ir/article_2366.html Background and Objectives: Vehicular Ad Hoc Networks (VANETs) face significant challenges due to high mobility and rapid topology changes. One of the most critical issues in this context is the clustering process, which directly impacts delay reduction, cluster stability, and overall network efficiency. However, traditional clustering methods such as K-Means and MFO, which mainly rely on simple metrics like distance or signal strength, fail to deliver optimal performance in dynamic environments with variable network density. The primary objective of this study is to design and evaluate an advanced clustering algorithm called AI_MCA (Artificial Intelligence Multi Clustering Algorithm), leveraging artificial intelligence and multi-criteria decision-making. By considering factors such as signal strength, relative speed, node density, and vehicle movement direction, the proposed algorithm forms clusters with higher stability and efficiency in dynamic and high-density environments.Methods: This study uses simulations to evaluate AI_MCA in VANETs, which facilitate vehicle-to-vehicle communication and are characterized by high mobility and rapid position changes.Results: Simulations in NS3 and SUMO show that AI_MCA reduces latency by 20% (12ms vs. 15ms in MFO) and improves cluster stability by 30% (lifetime of 45s vs. 33s in K-Means) within a 600m range. At a 1000m range with 300 nodes, delay increases to 14ms and PDR drops to 88%.Conclusion: AI_MCA outperforms traditional methods like K-Means and MFO, offering a scalable solution for VANET clustering. https://jecei.sru.ac.ir/article_2367.html Background and Objectives: Software testing plays a vital role in software development, aimed at verifying the reliability and stability of software systems. The generation of an effective test suite is key to this process, as it directly impacts the detection of defects and vulnerabilities. However, for software systems with numerous input parameters, the combinatorial explosion problem hinders the creation of comprehensive test suites. This research introduces a novel approach using the β-Hill Climbing optimizer, an advanced variant of the traditional hill climbing algorithm, to efficiently generate optimal test suites.Methods: The β-Hill Climbing optimizer introduces a dynamic parameter, β, which facilitates a precise balance between exploration and exploitation throughout the search process. To evaluate the performance of this proposed strategy (referred to as BHC), it is compared with TConfig as a mathematical approach, PICT and IPOG as greedy algorithms, and GS, GALP, DPSO, WOA, BAPSO, and GSTG as meta-heuristic methods. These strategies are tested across a variety of configurations to assess their relative efficiency.Results: The reported results confirm that BHC outperforms the others in terms of the size of generated test suites and convergence speed. The statistical analysis of the experimental results on several different configurations shows that BHC outperforms TConfig as a mathematical strategy, PICT and IPOG as greedy strategies, GS, GALP, DPSO, WOA, BAPSO, and GSTG as meta-heuristics by 83%, 88%, 87%, 61%, 61%, 46%, 61%, 62%, and 70%, respectively.Conclusion: The BHC strategy presents a novel and effective approach to optimization, inspired by β-Hill Climbing optimizer for the generation of optimal test suite. Its superior performance in the generation of test suites with smaller size and higher convergence speed compared to other strategies. https://jecei.sru.ac.ir/article_2390.html Background and Objectives: While intelligent vehicle teleoperation systems prioritize operational performance, their vulnerability to cyber-physical attacks—such as sensor spoofing and latency exploitation—remains a critical unsolved challenge. Existing solutions predominantly focus on attack prevention, leaving systems defenseless during active attacks that threaten stability and collision avoidance. This study addresses the unmet need for real-time resilience by introducing an adaptive control framework that dynamically mitigates attack-induced disruptions without relying on predefined vehicle models. Methods: We propose a novel adaptive LQR-based optimal controller that compensates for multi-vector attacks (e.g., false data injection, GPS spoofing) by estimating disturbed signals in real time. Unlike static models, our data-driven approach eliminates dependency on fixed dynamics. A rigorous case study evaluates performance under simultaneous command injection and DoS attacks, measuring trajectory deviation and recovery time. Results: The framework achieves ≤12% trajectory deviation (35% improvement over benchmarks) and 40% faster recovery from destabilizing attacks. It outperforms conventional controllers by adapting to model uncertainties and multi-vector threats without prior knowledge of system parameters. Conclusion: This work pioneers a model-agnostic, real-time resilience paradigm for teleoperated vehicles, merging human oversight with autonomous adaptability. Beyond immediate safety gains, it underscores the necessity of embedding cybersecurity-aware control mechanisms in connected vehicles, shifting from passive prevention to active threat mitigation. https://jecei.sru.ac.ir/article_2391.html Background and Objectives: In modern digital design, ternary logic gives simplicity and efficiency by reducing connectivity and chip area. This paper presents a new ternary decoder with only two ternary inverters and one binary NOR gate. One of the inverters is used simultaneously as a negative ternary inverter (NTI), and a positive ternary inverter (PTI) to attain circuit area reduction. Also, using the binary NOR instead of the ternary NOR eliminates don’t care states (middle voltage mode). The proposed decoder is implemented with complementary metal-oxide-semiconductor (CMOS), double pass logic (DPL), gate diffusion input (GDI), and pass transistor logic (PTL). In the proposed ternary decoder, the four mentioned technologies show an appropriate power delay product (PDP) and a smaller occupied area compared to the literature. Methods: In this paper, all simulations are performed using the 90 nm model, BSIM4 (level 54) version 4.4 by the HSPICE tool. The CMOS, DPL, PTL, and GDI techniques are used in the presented ternary decoder, and the results are extracted. The decoder shows good functionality compared to the previous research when implemented by these four circuits, but the best performance in terms of PDP results is from the CMOS.Results: The CMOS-based ternary decoder has only 10 transistors and shows the best results, its power consumption, and propagation delay are 25 μW and 0.07 ns, respectively. Besides, the number of transistors is reduced by 16.66% while it has 2 times increase in speed compared to the best decoders in previous research. The proposed high-speed and low-complexity decoder can be used in full adders (FAs) and digital signal processors (DSPs). Conclusion: Due to the application and advantage of ternary logic over binary, a ternary decoder with CMOS technique is designed that has fewer elements, a smaller area, and high speed compared to the existing ternary decoders. This new decoder includes only two ternary inverters and one binary NOR gate one of the inverters is used as a negative ternary inverter (NTI), and a positive ternary inverter (PTI), simultaneously. Also, the use of binary NOR gate eliminates don’t care states and reduces the circuit area. https://jecei.sru.ac.ir/article_2392.html Background and Objectives: Understanding the heterogeneity of breast cancer is crucial for improving treatment strategies. This study investigates the application of K-Means and Hierarchical Clustering to a local dataset of breast cancer patients from Iranmehr Hospital, Birjand, Iran, with the primary goal of identifying potential patient subgroups based on their clinical and treatment characteristics for knowledge discovery. The potential of these subgroups to inform future research on personalized treatment approaches is explored.Methods: A retrospective dataset comprising pathological and clinical information was analyzed using K-Means and Agglomerative Hierarchical Clustering to identify patient subgroups. The optimal number of clusters was consistently determined to be two (k=2) for both methods based on rigorous internal validation metrics (Elbow Method, Silhouette Analysis, Calinski-Harabasz Index, and Largest Jump Analysis for Hierarchical Clustering). Statistical tests (ANOVA and Chi-squared) were employed to assess significant differences in features across the identified clusters from both K-Means and Hierarchical analyses, providing insights into the key factors differentiating these groups. Internal cluster validity was assessed using Silhouette Score and Calinski-Harabasz Index.Results: The K-Means analysis identified two clusters exhibiting significant differences in characteristics such as age, chemotherapy session intensity, menopausal status, nodal involvement, and biomarker expression (ER, PR, HER2, Ki67). The Hierarchical Clustering also yielded two clusters with varying characteristics, and a comparison between the two methods highlighted both similarities and differences in the identified patient stratifications. The overall agreement between K-Means and Hierarchical Clustering was quantified by an Adjusted Rand Index (ARI) of 0.4697.Conclusion: Both K-Means and Hierarchical Clustering effectively revealed potential patient subgroups within the studied dataset, highlighting the heterogeneity of breast cancer presentation and treatment at a local level These clusters exhibited statistically significant differences across key clinical and treatment features. Future research is needed to validate these findings in larger, multi-center studies, explore the clinical significance of these subgroups in terms of treatment outcomes, and compare the effectiveness of different clustering methodologies for this purpose. https://jecei.sru.ac.ir/article_2393.html Background and Objectives: Massive Open Online Courses (MOOCs) face unique challenges in extracting student feedback from large, asynchronous student discussion forums. While traditional survey methods are commonly used, they struggle with scalability and real-time analysis in the MOOC context. This study aims to address these limitations and focus on automated extraction and classification of student opinions and their urgency. The study bridges the gap between suggestion mining in commercial applications and educational domains.Methods: We presented a novel deep learning approach using a BERT-based hybrid Convolutional Neural Network (CNN) – Bidirectional Long Short-term Memory (BiLSTM) multi-output model, named CBiLSTM. The model was trained to classify student posts into opinions and further categorize them by urgency. Performance metrics such as F1-weighted scores, Precision-Recall curves, and Area Under the Curve (AUC) were used to evaluate the model's efficacy, particularly in handling imbalanced datasets.Results: The presented CBiLSTM model got F1-weighted score of 87.3% for opinion classification and 81.1% for urgency classification which represents an improvement of 1.3% and 1.8% over the best-performing baseline model. Precision-Recall curves and AUC metrics highlights the model's strength in balancing precision and recall. These findings demonstrate the model's capacity to accurately classify and prioritize student feedback in the educational domain.Conclusion: This study offers a robust framework to enhance decision-making processes in MOOCs through effective feedback analysis. The CBiLSTM model provides a scalable, data-driven solution that empowers instructors, course designers, and policymakers to make targeted improvements, and improves student engagement and course quality. https://jecei.sru.ac.ir/article_2404.html Background and Objectives: The Internet of Things (IoT) serves as a fundamental communication model, enabling objects to deliver data and services to users. With the rapid expansion of IoT, ensuring privacy and preventing the disclosure of sensitive data during message exchanges between objects has become increasingly challenging. This paper presents an attribute-based framework designed to enhance privacy protection in IoT environments by leveraging software-defined networking (SDN) technology.Methods: By leveraging the SDN and the Attribute-Based Privacy Preserving (ABPP) model, our proposed framework employs an advanced algorithm to enhance privacy for client requests accessing IoT services. It focuses on protecting sensitive information during message transmission by implementing techniques for anonymity, unlinkability, and untraceability, tailored to the sensitivity level of each message. To further enhance message privacy within the IoT network, our framework incorporates IP aliasing, dynamic channel switching, and payload encryption.Results: Our proposed framework significantly enhances privacy protection in IoT networks by dynamically applying anonymity and concealment techniques tailored to the sensitivity of CoAP messages. Simulation results using CloudSimSDN confirm the framework's effectiveness in safeguarding sensitive information while maintaining optimal communication performance. Employing three privacy-preserving techniques results in an average CPU utilization that is 0.14 units higher compared to using a single technique. We provide a security evaluation that includes formal verification techniques and informal analysis, and show that the proposed framework is secure against anonymity and MITM attacks, replay attacks, Sybil, and IP spoofing.Conclusion: In this paper, we present a four-layer SDN-based framework designed to enhance privacy in IoT networks through the use of the Attribute-Based Privacy Preserving (ABPP) model. The framework employs IP aliasing, dynamic routing, and content encryption techniques tailored to the sensitivity of CoAP messages to ensure data protection. Our implementation and experiments conducted with CloudSimSDN validate the framework's effectiveness in safeguarding sensitive information. https://jecei.sru.ac.ir/article_2409.html Background and Objectives: The objective of this study is to achieve fast finite-time control of DC-DC buck converters by designing a robust-adaptive terminal sliding-mode controller utilizing a fractional-order control strategy combined with a state-disturbance observer. The work begins by considering that all dynamic parameters of the converter circuit, such as resistance, capacitance, and inductance, are completely unknown due to significant uncertainties.Methods: To formulate the stabilizing fractional-order sliding mode controller, the fractional-order sliding surface is initially presented. Given the absence of knowledge about the converter's dynamic parameters, an adaptive fractional-order finite-time sliding mode controller is developed to ensure the finite-time stability of the system and to achieve rapid convergence of the converter voltage to the prescribed reference value in the presence of parameters uncertainties and external disturbances. To estimate unknown varying parameters in the converter, an adaptive law is additionally designed. Furthermore, a high-speed observer is incorporated to estimate both external disturbances and the state variables affecting the system. An analysis is also presented to find the maximum allowable sampling time based on the controller parameters.Results: The closed-loop system stability is validated through the application of the extended Lyapunov method. Importantly, the proposed method ensures that the output voltage of the converter reaches its desired value within a finite time taking external disturbances into account as well as operating with unknown parameters, and also, without direct feedback from voltage or current measurements. Ultimately, simulation results along with some enhanced robustness analysis are presented to demonstrate the effectiveness of the proposed control approach. Conclusion: The innovative controller based on fractional-order sliding mode control in a sensor less DC-DC buck converters is considered. The goal is to converge the output voltage to the desired value in finite time considering that all of the converter dynamic parameters are unknown and system is exposed to external disturbances. Chattering is reduced using a new technique and the maximum allowable sampling time is also obtained. The results validate the suitability of the proposed technique especially in overcoming against uncertainties and disturbances without requiring voltage/current measurements. https://jecei.sru.ac.ir/article_2411.html Background and Objectives: This paper presents a high-performance and efficient circuit based on low-cost coils for induction heating applications. We design the coils specifically for induction sealing and induction cooker applications. The proposed circuit utilizes two parallel sets of MOSFET transistors to increase the current flow and output power.Methods: Three types of coils have been developed in square and rectangular designs on the printed circuit board (PCB). In this case, the construction process is simple and requires minimal time. Induction coils designed for induction sealing applications have a rectangular structure that effectively seals a wide range of bottles.Results: The flexibility of the proposed circuit is one of its advantages; the output frequency can be adjusted by increasing or decreasing the number of capacitors in the capacitor bank. Performance comparisons (e.g., efficiency, power density, cost) between the proposed method and other studies show that the implementation cost of the proposed circuit is lower than that of others. The proposed circuit achieves 95% efficiency. Thermal imaging confirms the circuit's performance. Based on the electromagnetic interference results, the circuit's performance is not affected by an external magnetic field.Conclusion: The proposed circuit has been tested with different capacitor banks using two power supplies of 24 V and 12 V. The peak-to-peak output voltage is 181 V and 92 V for the 24 V and 12 V power supplies, respectively. The results demonstrate that the circuit and coils are suitable for induction heating applications. https://jecei.sru.ac.ir/article_2426.html Background and Objectives: Sonar data processing helps in identifying and tracking targets with unstable echoes, which conventional tracking methods often misidentify. Recently, RLA has significantly improved the accuracy of undersea target detection compared to traditional sonar object recognition techniques that tend to lack robustness and precision.Methods: This research utilizes a combination of classifiers to improve the accuracy of Sonar data classification for complex tasks like identifying marine targets. Each classifier creates its own data pattern and maintains a model. Ultimately, a weighted voting process is carried out by the fuzzy learning automata algorithm among these classifiers, with the one receiving the highest votes being the most impactful on performance improvement.Results: We compared the performance of SVM, RF, DT, XGBoost, ensemble methods, R-EFMD, T-EFMD, R-LFMD, T-LFMD, ANN, CNN, TIFR-DCNN+SA, and joint models against the proposed model. Given the differences in objectives and databases, we focused on benchmarking the average detection rate. This comparison examined key parameters including Precision, Recall, F1_Score, and Accuracy to highlight the superior performance of the proposed method compared to the others.Conclusion: The results obtained with the analytical parameters Precision, Recall, F1_Score and Accuracy have been examined and compared with the latest similar research and the values of 88.6%, 90.2%, 89.02% and 88.6% have been obtained for each of these parameters in the proposed method, respectively. Also, in this research, the impressive performance of the new method compared to the Sonar data fusion by the conventional learning automata method is evident. https://jecei.sru.ac.ir/article_2428.html Background and Objectives: Currently, the control engineering community is increasingly focusing on research related to Unmanned Aerial Vehicles (UAVs) due to their versatile capabilities. Among the various applications, target detection and tracking stand out as crucial. Recent advancements in Artificial Intelligence (AI) and Deep Learning (DL) have the potential to enhance the synergy between vision and control in UAV operations. By integrating AI algorithms with control methods, the accuracy of target information can be significantly improved in UAVs. This research introduces an autopilot system for quadcopters to search for and track a predetermined target.Methods: The autopilot system utilizes the YOLO network, a robust convolutional neural network-based system, for real-time target detection. To enhance object tracking robustness, the Kalman filter is integrated into the system. Furthermore, Proportional-Derivative (PD) controllers are utilized to calculate suitable control commands, enabling the quadcopter to effectively track both stationary and moving targets. Additionally, an object retrieval strategy is proposed to locate and recover lost objects during the tracking phase. Results: The effectiveness of the proposed system was evaluated through real-time experimental trials involving diverse scenarios encompassing both stationary and moving targets. The integration of the YOLOv5 network with the Kalman filter substantially improved detection accuracy and stability. Furthermore, the object retrieval mechanism demonstrated high reliability in recovering lost targets, thereby increasing overall system resilience. The PD-based control scheme enabled responsive and precise trajectory adjustments, contributing to consistent target tracking performance across all test cases.Conclusion: Integration of a YOLOv5-based detection module, a Kalman filter for robust tracking, and PD controllers for flight control provides an autonomous quadcopter system capable of detecting and tracking both stationary and moving targets with unknown dynamics. The proposed approach shows promise for real-time autonomous tracking applications and offers a foundation for future development in more complex, outdoor scenarios. https://jecei.sru.ac.ir/article_2429.html Background and Objectives: Accurate measurement of moisture content (MC) in wheat grains is vital for quality control and storage management. This study presents the development of a differential microwave sensor with enhanced sensitivity for detecting MC in wheat grains, leveraging resonant techniques to improve detection precision.Methods: The proposed sensor utilizes two identical half-wavelength (λ/2) microstrip resonators symmetrically coupled to a standard 50Ω transmission line. One resonator serves as a reference with a relative permittivity (έr) of 1, while the second is exposed to the sample under test (SUT), where έr > 1. This differential structure enables the identification of dielectric property changes due to moisture variation. The operating principles are theoretically analyzed using even- and odd-mode techniques.Results: The proposed sensor exhibits three distinct transmission zeros (TZs) within the 0.1–2 GHz frequency range, which arise from the harmonic behavior of the resonators. A prototype was fabricated on a low-cost, compact substrate with dimensions of 6 × 4.5 × 0.16 cm³ and was experimentally tested, confirming the simulation results. The sensor demonstrates a high normalized sensitivity of 7.63%.Conclusion: The developed differential microwave sensor demonstrates strong potential for precise and reliable MC detection in wheat grains. Its compact design, cost-effectiveness, and high sensitivity make it a suitable candidate for practical agricultural and food monitoring applications. https://jecei.sru.ac.ir/article_2430.html Background and Objectives: Impedance source networks have gained significant attention in electrical energy conversion due to their ability to overcome the limitations of conventional methods. While existing impedance-based converters offer various advantages, challenges such as voltage gain limitations and component stress remain. This study introduces an advanced ultra-gain enhanced A-source (UGEA-S) DC/DC converter incorporating switched-capacitor technology to address these concerns and significantly improve voltage gain.Methods: The proposed UGEA-S converter is designed to enhance energy conversion efficiency while minimizing voltage stress on switching elements. The topology integrates switched-capacitor techniques to achieve superior voltage gain, reducing reverse recovery issues in diodes and maintaining a continuous input current. A thorough theoretical analysis is conducted to explore its operational principles and steady-state behavior. Comparative assessments with other recently developed converters further highlight its distinct performance attributes. Additionally, MATLAB/Simulink simulations and experimental results are performed to validate the converter’s functionality under practical operating conditions.Results: Experimental, simulation and numerical analysis confirm that the proposed UGEA-S converter achieves an ultra-high voltage gain of up to 8× (480 V output from a 60 V input) while maintaining low voltage stress across switching components. The MOSFET experiences a peak voltage of 230 V and a current of 28 A, well within safe operating limits. Diodes D1–D4 exhibit voltage stresses ranging from 230 V to 520V, with average currents between 2.65 A and 20.3 A. The input inductor sustains a continuous current of 19.5 A, validating the converter’s smooth current profile. Efficiency measurements show a peak of 96.93% at 230 W output, with performance remaining above 92% even at full 1 kW load. These results demonstrate the converter’s resilience under dynamic conditions and its suitability for high-performance applications such as electric vehicles and renewable energy systems.Conclusion: The UGEA-S converter offers a robust and innovative solution for high-gain DC/DC conversion, addressing key limitations of conventional designs. Its exceptional voltage gain, reduced voltage stress, and stable current regulation make it a promising candidate for advanced energy systems. The findings underscore the converter’s feasibility for real-world applications, particularly in electric vehicle power systems. Future research can further optimize its design for enhanced efficiency and broader scalability. https://jecei.sru.ac.ir/article_2431.html Background and Objectives: Multiphase electric motors are useful for industrial and military applications that need high power, smooth torque and the ability sharing power and torque in comparison to conventional three-phase electric motors. Also, these motors a more suitable substitute than three-phase motors because of their ability to manage fault condition, guaranteeing the postfault operation of the drive. One type of Multiphase electric machines is Permanent Magnet Brushless Motors (PMBLM) that due to the inevitable limitations in their construction, back-EMF voltages are neither sinusoidal nor trapezoidal. Using traditional control strategies of and Brushless DC Motors (BLDCM) and Permanent Magnet Synchronous Motors (PMSM) results high electromagnetic torque ripple, vibrations and noises that are undesirable for medium voltage applications. Methods: This paper suggests a new finite control set model predictive control (FCS-MPC) method for two diode-clamped three-level (DC3L) inverters fed non-sinusoidal dual three phase PMBLM (DTP-PMBLM) with the capability to manage pre-fault conditions for reduction torque ripple and withstand postfault situations. The suggested MPC method removes requirement of weighting factor in the cost function for neutral point voltages in both DC3L inverters with a simple scheme balancing of capacitive voltages. Also, the fault tolerant control (FTC) schemes open phase fault and open switch fault are considered.Results: To study the effectiveness of the suggested MPC method, simulation results non-sinusoidal DTP-PMBLM drive are investigated and compared to with multiband hysteresis current (MHC) controller. Simulations have been carried out using MATLAB/Simulink with specifications 4125-V/2.7MW/350-RPM. Conclusion: Simulation results validate that the suggested MPC method has great dynamic responses such as lower torque ripple than the MHC controller. The FTC schemes are implemented without complexity changing the mathematical model and control framework. https://jecei.sru.ac.ir/article_2455.html 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. https://jecei.sru.ac.ir/article_2456.html 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. https://jecei.sru.ac.ir/article_2457.html 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. https://jecei.sru.ac.ir/article_2458.html 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. https://jecei.sru.ac.ir/article_2459.html 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. https://jecei.sru.ac.ir/article_2427.html Background and Objectives: Cloud computing can play a vital role in promoting environmental sustainability by leveraging eco-friendly dedicated servers that adhere to green computing standards. The concept of "green cloud computing" revolves around harnessing cutting-edge technologies to minimize the environmental footprint of computing systems. One of the significant challenges in cloud-based systems is task scheduling, which must be optimized to enhance system efficiency, user experience, and environmental sustainability.Method: This paper proposes a novel Hybrid HEES (Hierarchical Energy-Efficient Scheduling) method that optimizes energy consumption and task scheduling in cloud computing environments. By combining genetic algorithm optimization, workflow-based scheduling, and energy-aware resource allocation, HEES achieves significant reductions in energy consumption and average task completion time.Results: The method is evaluated through simulations, demonstrating its effectiveness in optimizing energy efficiency and task scheduling performance. The Hybrid HEES method has the potential to reduce energy consumption, improve computing performance, and enhance sustainability in cloud computing environments.Conclusion: To evaluate a proposed HEES method through cloudsim 3.0 simulations, the numerical results confirm the effectiveness of HEES algorithm, which achieves average Energy consumption performance improvements of around 12% compared to GP and 8% compared to RR existing methods. https://jecei.sru.ac.ir/article_2492.html 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. https://jecei.sru.ac.ir/article_2493.html 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. https://jecei.sru.ac.ir/article_2539.html 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. https://jecei.sru.ac.ir/article_2540.html 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. https://jecei.sru.ac.ir/article_2541.html 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. https://jecei.sru.ac.ir/article_2542.html 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. https://jecei.sru.ac.ir/article_2543.html 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. https://jecei.sru.ac.ir/article_2544.html 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. https://jecei.sru.ac.ir/article_2545.html 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. https://jecei.sru.ac.ir/article_12554.html 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. https://jecei.sru.ac.ir/article_12555.html 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.