IEEE Canadian Journal of Electrical and Computer Engineering最新文献

{"title":"Performance Analysis of Intelligent Classifiers for High Impedance Fault Detection in a PV-Integrated IEEE-13 Bus System","authors":"Najwa Nasuha Mahzan;Mohammad Lutfi Othman;Noor Izzri Abdul Wahab;Veerapandiyan Veerasamy;Nur Ashida Salim;Aidil Azwin Zainul Abidin;Syed Zahurul Islam","doi":"10.1109/ICJECE.2024.3469216","DOIUrl":"https://doi.org/10.1109/ICJECE.2024.3469216","url":null,"abstract":"High impedance faults (HIFs) present significant challenges in power systems, particularly when an electrical wire contacts a high-resistance material, leading to low currents that are difficult for traditional relays to detect. With the increasing integration of photovoltaic (PV) systems, these challenges are exacerbated due to the complex behavior of PV-generated signals. This study aims to enhance the detection of HIFs in PV-integrated systems using advanced machine learning techniques. The approach employs various classifiers, including artificial neural networks, support vector machines (SVMs), decision trees, and random forest (RF) to improve fault identification accuracy. A MATLAB/SIMULINK simulation was conducted on an IEEE 13-bus system with a 300-kW solar PV plant. The discrete wavelet transform (DWT) with the db4 wavelet was used for feature extraction, focusing on phase energy values. The classifiers were evaluated under different scenarios, such as normal operation, load switching (LS), capacitor switching (CS), HIF, and line-to-ground (LG) faults. The RF classifier outperformed others, achieving a fault detection accuracy of 99.4083%, demonstrating its robustness in adapting to various fault conditions. The Naive Bayes (NB), multilayer perceptron (MLP), and logistic regression (LR) classifiers achieved lower accuracies of 78.6982%, 76.9231%, and 80.4734%, respectively. These results indicate a significant improvement in fault detection capability, enhancing the stability, reliability, and resilience of electrical grids integrated with PV systems. The findings suggest that the RF classifier is highly effective for HIF detection, which is crucial for the protection and efficient operation of modern power grids with high renewable energy penetration.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"98-108"},"PeriodicalIF":2.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Intelligent Handwriting and Painting Teaching System Based on Artificial Intelligence Edge Computing Technology","authors":"Liang-Bi Chen;Xiang-Rui Huang;Hsin-Yu Chen","doi":"10.1109/ICJECE.2025.3550383","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3550383","url":null,"abstract":"In this article, a handwriting teaching system based on artificial intelligence (AI) edge computing technology is proposed. The proposed system combines gesture tracking, gesture recognition, and other related AI technologies. Additionally, the development platform for AI edge computing in this system is developed to teach handwriting and practice drawing. The proposed system is composed of a teacher-end teaching host and several student-end AI edge computing smart devices. The student-end AI edge computing smart device incorporates virtual drawing and writing, finger digital computing teaching, a virtual keyboard, virtual sliding, and sleep prevention warnings. The teacher-end teaching host allows the teacher to conduct a teaching course. Moreover, the teacher-end teaching host and the student smart device can simultaneously display images on a large screen to facilitate teaching demonstrations. Furthermore, this system has a comprehensive data storage cloud platform, which can record the data uploaded by each student to a storage cloud platform to facilitate teaching evaluations. This work differs from traditional handwriting and painting technique studies in the classroom, and the AI virtual drawing technology proposed in this work can produce impressive visual effects for visual media, including animation, graphics, and text.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"87-97"},"PeriodicalIF":2.1,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and Analysis of an Online and Offline Wide-Area Control System With Limited Generators","authors":"Nagasekhara Reddy Naguru","doi":"10.1109/ICJECE.2025.3542062","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3542062","url":null,"abstract":"The objective of this work is to compare the performances of online and offline wide-area control system designs by considering the limited number of generators. The design of the controller feedback gain matrix in both techniques is achieved by the state feedback control technique. Both designs are implemented with a limited number of generators. However, the required structure of the feedback gain matrix in offline mode can be accomplished by using the structurally constrained H2-norm optimization. On the other hand, the required gain matrix in online mode can be designed with the help of a real-time control input matrix, right and left eigenvectors. The phasor measurement units (PMUs) data is used in both designs. Both the state vector and the feedback gain matrix are computed in real-time in online mode. Whereas in offline mode, only the state vector is obtained from PMU measurements and the feedback gain matrix can be designed with the help of available offline data of a particular test system. The merits and demerits of both designs are explained in detail by considering different aspects. The comparison of the performances of both designs is illustrated in MATLAB/Simulink environment by considering the IEEE-68 bus test system.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"78-86"},"PeriodicalIF":2.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel Switched Mode OAM Beam Generation Using Series-Fed UCA Antenna for AAVs Nouvelle génération de faisceau MAO en mode commutéà l’aide d’une antenne UCA alimentée en série pour les AAVs","authors":"Madasu Venkateswara Rao;Arif Mawardi Ismail;Mohd Najib Mohd Yasin;Shehab Khan Noor;Mohamed Nasrun Osman;NA Abd Rahman;Jagannath Malik;S. Yuvaraj","doi":"10.1109/ICJECE.2025.3539782","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3539782","url":null,"abstract":"Designing planar antenna with orbital angular momentum (OAM) radiation beam is quite challenging. Adding mode configurability in the OAM antenna further increases the complexity for practical realization. This article presents a novel modified single-fed uniform circular array (UCA) antenna capable of generating three OAM modes (l = −1, +1, and 0). These modes can be controlled electronically using three p-i-n diodes in real-time. A series-fed network with eight circularly polarized (CP) patches generates −1 and +1 OAM modes depending on two possible ways of excitation (i.e., clockwise or counterclockwise). Two-element linearly polarized (LP) array placed at the center of the UCA antenna generates l = 0 OAM mode. The CP elements are rotated sequentially along a circle maintaining 45◦ between two consecutive elements to obtain the desired phase excitation. The final optimized antenna was fabricated on an FR4 substrate with the p-i-n diode switches. The experimental results show that the proposed UCA antenna successfully generates the desired OAM modes at 6 GHz. The proposed concept offers simple OAM mode reconfigurability and can be scaled to operate at other frequencies, making it advantageous for various vehicular and wireless communication applications. Résumé—La conception d’une antenne planaire avec un faisceau de rayonnement à moment angulaire orbital (MAO) est un véritable défi. L’ajout d’un mode configurable dans l’antenne à MAO augmente encore la complexité de la réalisation pratique. Cet article présente une nouvelle antenne réseau circulaire uniforme (UCA) modifiée à alimentation unique capable de générer trois MAO (l = −1, +1, et 0). Ces modes peuvent être contrôlés électroniquement à l’aide de trois diodes pin en temps réel. Un réseau alimenté en série avec huit patchs à polarisation circulaire (PC) génère des modes MAO −1 et +1 selon deux modes d’excitation possibles (c’est-à-dire dans le sens des aiguilles d’une montre ou dans le sens inverse). Un réseau à deux éléments à polarisation linéaire (PL) placé au centre de l’antenne UCA génère un mode MAO l = 0. Les éléments PC sont tournés séquentiellement le long d’un cercle en maintenant 45◦ entre deux éléments consécutifs pour obtenir l’excitation de phase souhaitée. L’antenne optimisée finale a été fabriquée sur un substrat FR4 avec des commutateurs à diode pin. Les résultats expérimentaux montrent que l’antenne UCA proposée génère avec succès les MAO souhaités à 6 GHz. Le concept proposé offre une reconfiguration simple des MAO et peut être adapté pour fonctionner à d’autres fréquences, ce qui le rend avantageux pour diverses applications de communication véhiculaire et sans fil.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"60-65"},"PeriodicalIF":2.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Compliance Control of Biped Robot Considering Position Tracking and Task Priority","authors":"Sheng Dong;Feihu Fan;Jingchao Li;Jianrui Zhang;Yinuo Chen","doi":"10.1109/ICJECE.2025.3542792","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3542792","url":null,"abstract":"In this work, we propose a joint force control framework for the stable motion of a humanoid biped robot. In motion planning, nonlinear centroid dynamics is used to generate gait on uneven terrain, which overcomes the limitation of a linear inverted pendulum (IP) model on centroid height. The motion control layer combines multipriority inverse kinematics (MPIK) and multipriority dynamic control (MPDC). The MPIK uses a multipriority inverse kinematics numerical iteration algorithm to calculate joint position command. The MPDC uses a multipriority iterative optimization method based on the task-space dynamics model on the forward path, which does not need preallocation or preoptimization of contact force, does not explicitly control the movement of center of mass (CoM), and tries its best to complete high-priority tasks. Finally, a stable joint compliance force control framework is built, and the introduction of kinematic error information ensures the accurate position tracking of the force control system. The results show that the control strategy completes the task of climbing stairs well and shows a certain antidisturbance ability in standing still and variable speed walking. The maximum disturbance in the sagittal plane can reach 50 N·s (achieved solely by adjusting the position of the pressure center and without using the step stability strategy).","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"66-77"},"PeriodicalIF":2.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Enhanced Co-Prime Sampler for Effective Coarray-Domain Processing of Underdetermined Direction-of-Arrival Estimation","authors":"Ashok Chandrasekaran;N. Venkateswaran","doi":"10.1109/ICJECE.2025.3562971","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3562971","url":null,"abstract":"The design of a sparse sampler for effective coarray-domain processing of underdetermined direction-of-arrival (DOA) estimation is of prime research interest. Toward this, several sparse samplers have been proposed, among which co-prime samplers have garnered significant attention due to their closed-form expression for sampler element positioning and minimal susceptibility to mutual coupling effects. In this article, an enhanced co-prime sampler (ECPS) is proposed by concatenating the two operations on subsamplers, involving the scaling of one subsampler and shifting of another subsampler within the hold of the co-prime property. The proposed ECPS offers several advantages over existing samplers, including increased consecutive lags, reduced holes in the difference coarray, larger physical aperture, enhanced sparsity, and reduced susceptibility to mutual coupling effects. These improvements lead to high consecutive degrees-of-freedom (cDOF) in detecting more targets than the number of physical elements in the sampler with high estimation accuracy. The superiority and efficacy of the proposed ECPS are analyzed and validated with several simulation studies.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"124-130"},"PeriodicalIF":2.1,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sidewalk Extraction on Aerial Images With Deep Learning and Path Planning Algorithm Extraction de trottoirs à partir d’images aériennes à l’aide de l’apprentissage profond et d’un algorithme de planification de trajectoire","authors":"Zhibin Bao;Haoxiang Lang;Xianke Lin","doi":"10.1109/ICJECE.2025.3561698","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3561698","url":null,"abstract":"High-definition (HD) maps play an important role in autonomous driving by providing vehicles with localization functionality, environmental information, and support its mission and motion planning. In an HD map, road network extraction/annotation is a crucial feature that helps the autonomous vehicle navigate and keeps it within the safe driving zone. While road network extraction traditionally focuses on motorways and their boundaries, the emergence of small-scale autonomous vehicles, such as delivery and service robots, has shifted attention to sidewalks. Sidewalks are critical for safe and efficient navigation in residential and urban areas, yet automated methods for sidewalk extraction remain underexplored. To address this gap, this article proposes a sidewalk extraction method on aerial images using deep learning with the transfer learning technique. A path-planning algorithm-based refinement method is also proposed to further refine the extracted sidewalk. The proposed method can precisely extract sidewalks from aerial photographs and fix sidewalk discontinuity issues caused by occlusions. A sidewalk dataset is also explicitly designed for sidewalk extraction and semantic segmentation research. This article’s work is meant to fill the sidewalk extraction gap for road network extraction.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"115-123"},"PeriodicalIF":2.1,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IEEE Canadian Journal of Electrical and Computer Engineering","authors":"","doi":"10.1109/ICJECE.2025.3539555","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3539555","url":null,"abstract":"","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 1","pages":"C2-C2"},"PeriodicalIF":2.1,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10931807","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rainfall Classification Using Machine Learning Algorithms on Data Mining Platforms","authors":"Sevtap Turk","doi":"10.1109/ICJECE.2025.3558882","DOIUrl":"https://doi.org/10.1109/ICJECE.2025.3558882","url":null,"abstract":"Weather conditions directly affect sectors such as agriculture and transport. With climate change, unpredictability is increasing and traditional calculation methods may not be sufficient. In addition to some statistical methods, machine learning algorithms are also used for weather forecasting. This study attempts to classify precipitation using machine learning algorithms on selected meteorological data. The models used are K-nearest neighbors (KNNs), support vector machine (SVM), and multilayer perceptron (MLP). These models were implemented on four different open-source and free data mining platforms. These platforms are Altair AI Studio (formerly Rapidminer), Knime, Orange, and Weka. The dataset includes parameters such as pressure, temperature, humidity, number of rainy days, cloudiness rate, and year and month information. According to the values of these parameters, the data were classified as less rainy, rainy, and very rainy.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 2","pages":"109-114"},"PeriodicalIF":2.1,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144090742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Quadrilateral Self-Isolated Wideband MIMO SIW Fractal Koch Snowflake Slot Antenna Array for Ka-Band Communications","authors":"Elagandula Aparna;Gopi Ram;G. Arun Kumar","doi":"10.1109/ICJECE.2024.3523098","DOIUrl":"https://doi.org/10.1109/ICJECE.2024.3523098","url":null,"abstract":"This work proposes a new approach to design a quadrilateral self-isolated multiple-input–multiple-output (MIMO) antenna configuration operating for reliable <inline-formula> <tex-math>$Ka$ </tex-math></inline-formula>-band communications. The proposed design utilizes a single-layer substrate integrated waveguide (SIW) fractal Koch snowflake (FKS) slot antenna array. The main focus is on achieving wideband characteristics and self-isolation among antennas without using any additional isolation circuits. The method is described to obtain the wideband performance of the SIW FKS slot antenna array fed with a grounded coplanar waveguide (GCPW). The radiation performance of single-element and quadrilateral elements is analyzed. The simulation and measurement results demonstrate that the MIMO antenna elements exhibit a bandwidth of 27.1–32.4 GHz (17.8%) and peak gain of 8.3 dBi at 28 GHz. The achieved isolation levels are greater than 23 dB (simulated) and 20 dB (measured), with a self-isolation structure. Furthermore, this work extended to calculate diversity characteristics of proposed MIMO, such as the envelope correlation coefficient (<inline-formula> <tex-math>$text {ECC} lt 0.005$ </tex-math></inline-formula>), mean effective gain ratio (<inline-formula> <tex-math>$text {MEG} lt 1.1$ </tex-math></inline-formula>), diversity gain (<inline-formula> <tex-math>$text {DG}lt 9.9$ </tex-math></inline-formula> dB), and channel capacity loss (<inline-formula> <tex-math>$text {CCL}lt 0.3$ </tex-math></inline-formula> bits/s/Hz). These results validate that the proposed MIMO antenna design is performing satisfactorily. The fabricated prototype measurement results are validated with simulation results.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"48 1","pages":"52-59"},"PeriodicalIF":2.1,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}