IEEE Latin America Transactions最新文献

{"title":"Dense-PMSFNet: DenseNet Pyramidal Multi-Scale Fusion Network for Retinal Vasculature and FAZ Segmentation in OCTA Images","authors":"Nisan Pranavah Raja;Srivatsan Sarvesan;Anju Thomas;Varun P Gopi","doi":"10.1109/TLA.2025.10930374","DOIUrl":"https://doi.org/10.1109/TLA.2025.10930374","url":null,"abstract":"Diabetic retinopathy (DR) is a condition that leads to damage to the retina due to high blood sugar levels in the eyes caused by prolonged diabetes. People of working age in developing countries are particularly at risk of developing diabetic retinopathy, which causes permanent vision loss in diabetic patients. Diagnosis involves maintaining the current level of vision of the patient, as the disease can cause blindness. Optical Coherence Tomography Angiography (OCTA) is an advanced eye imaging technique that offers a detailed view of the structures of retinal blood vessels and effectively treats various eye conditions. Therefore, it is crucial to accurately identify and separate the capillary, artery, vein, and Foveal Avascular Zone (FAZ) from OCTA images. The DenseNet Pyramidal MultiScale Fusion Network (Dense-PMSFNet) is introduced in this article as a new segmentation network based on deep learning. It utilizes the DenseNet Encoder to integrate local semantic contextual information, the Multi-Scale Pyramidal Fusion Module (MSPFM) to effectively merge local features at different scales, and Deep Fusion to enhance the representation of multiscale decoder outputs. Through extensive experimentation on four distinct segmentation tasks involving capillary, artery, vein, and FAZ from OCTA images, it has demonstrated superior performance for the quantitative metrics such as Dice coefficient (DSC), Accuracy (ACC), Intersection Over Union (IoU), Specificity (SP) and Sensitivity (SE) in comparison to state-of-the-art methods.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 4","pages":"312-322"},"PeriodicalIF":1.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10930374","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143637967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Phasor Modeling of the Single-Phase MMC under Modulation PSC-PWM","authors":"Glendy A. Catzin-Contreras;Gerado Escobar;Andres Alejandro Valdez-Fernandez;Manuel J. Lopez-Sanchez","doi":"10.1109/TLA.2025.10930370","DOIUrl":"https://doi.org/10.1109/TLA.2025.10930370","url":null,"abstract":"This paper develops a model, based on the dynamic phasor approach, for the single-phase modular multilevel converter (MMC), where the switching sequences are generated by the phase-shifted carrier-based pulse-width modulation (PSC-PWM) scheme. The modeling process begins with the MMC state space model, from which the DC and the fundamental complex Fourier coefficients, called dynamic phasors, are extracted for both the original state variables and the switching functions. It is worth noting that, in the developed dynamic phasor-based model (DPhM) of the MMC, all capacitor voltages per phase are considered separately in the modeling process, which contrast with the usual definition of variables based on the sum and difference of the capacitor voltages on the arms. Experimental results are presented to demonstrate the validity of the MMC DPhM as compared to the response of the switched MMC under the PSC-PWM scheme. In particular, it is observed that the developed MMC DPhM is able to reproduce the steady-state waveforms of all original state variables, including the ripple amplitude, as compared to the results obtained with the switched MMC. Furthermore, it is shown that, both in the switched MMC under the PSC-PWM and in the derived DPhM MMC, all capacitors converge to the same steady-state average value without adding an external balance controller, but only due to the natural balancing action of the PSC-PWM scheme, despite arbitrary initial conditions of capacitor voltages.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 4","pages":"353-361"},"PeriodicalIF":1.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10930370","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143637986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Memetic Genetic Particle Swarm Optimization for Druglike Molecule Discovery","authors":"Matías Gabriel Rojas;Ana Carolina Olivera;Pablo Javier Vidal","doi":"10.1109/TLA.2025.10879174","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879174","url":null,"abstract":"Given the vast and complex chemical search space, developing new techniques for identifying promising ligands that satisfy multiple objectives is highly desirable to reduce the costs and times required for effective drug discovery. Neural networks are frequently employed for this task, but they tend to generate molecules that are invalid both chemically and syntactically. As an alternative, metaheuristics have emerged as promising approaches, delivering notable results with reasonable computational costs. However, they often suffer from information loss during the process, leading to poor quality generations. In this work, we introduce a novel memetic algorithm that hybridizes Particle Swarm Optimization with Simulated Annealing. This approach aims to improve the balance between exploration and exploitation in the de-novo drug discovery process, ensuring that promising molecules are not overlooked during generation steps. We compare our approach against six state-of-the-art algorithms, and the results demonstrate that our algorithm enhances molecule generation quality, showing an increased diversity and improved chemical properties of the resulting ligands.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"216-222"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879174","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Table of Contents March 2025","authors":"","doi":"10.1109/TLA.2025.10879179","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879179","url":null,"abstract":"","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"181-181"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879179","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Agreement analysis of heart rate variability indices at two different sampling rates for monitoring applications.","authors":"Eduardo San Roman;Javier Zelechower;Jose Manuel Gallardo;Marcelo Risk","doi":"10.1109/TLA.2025.10879195","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879195","url":null,"abstract":"Beat-to-beat variations in heart rate lead to heart rate variability (HRV), analysed from electrocardiogram or photoplethysmography signals, forming a non-equispaced time series of beats, which requires a resampling of 3 Hz or 4 Hz, for analysis in the frequency domain. HRV is considered a biomarker, predictor of the evolution of diseases in intensive care units (ICU). To enhance these HRV studies, it is necessary to monitor the patients health using portable devices, from admission to the ICU until discharge from it and subsequently at home. This requires monitoring devices that can minimise energy consumption and data storage. Reducing the sampling frequency in HRV can reduce energy consumption, computing power and to limite data storage. Therefore, the objective of this work is to prove that a series resampled at 1 Hz allows obtaining HRV indices, equivalent to a 3 Hz. Through concordance analysis, using a database of subjects with pharmacological autonomic blockade and postural changes. The results show equivalences between the indices, standard deviation (SDNN), total spectral power (PT), low frequency (LF) and long-term variability (SD2) and agree with those reported as predictors. This study has limitations, since only a small number of young men participated. Future studies should consider this. The reduction of SDNN, PT, LF values would be predictors of mortality in hospitals, so the equivalence found from series with 1Hz resampling, would allow the use of portable devices with optimized performance, to monitor the evolution of the disease in patients in ICUs.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"258-264"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879195","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UAV Flight Comparison Using Backstepping: On-board Data and Observers","authors":"Jesus Santiaguillo-Salinas;Eduardo Aranda-Bricaire;Hiram N. Garcia-Lozano","doi":"10.1109/TLA.2025.10879177","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879177","url":null,"abstract":"This paper presents the comparison of performance in flight trajectory tracking for a commercial UAV AR.Drone 2.0, using state observers and on board data. This work seeks to establish that state observers are an alternative to close the control loop in this type of applications. The control strategy proposed for the flight is designed using the Backstepping technique. For the implementation of the control law, knowledge of the position and orientation of the UAV is assumed, therefore, its longitudinal and rotational velocities are estimated either by using observers or data from the combination of inertial and visual measurement of the on-board sensors. In both cases, the designed control strategy makes the UAV converge to the pre-established flight trajectory. However, an analysis of the mean square error between the UAV trajectory with respect to the desired trajectory, gives as a result that, in three of the four compared states, the error obtained with the observer is lower. The theoretical results presented are validated experimentally.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"182-190"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879177","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Convolutional Neural Networks using the SMOTE Algorithm and Features Fusion for Wind Turbine Fault Prediction","authors":"Lucas França Aires;Júlio Oliveira Schmidt;Guilherme Ricardo Hübner;Frederico Menine Schaf;Claiton Moro Franchi;Humberto Pinheiro;Daniel Fernando Tello Gamarra","doi":"10.1109/TLA.2025.10879178","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879178","url":null,"abstract":"This research introduces an innovative method using Convolutional Neural Networks (CNNs) to identify mass imbalances in wind turbine rotors through a feature fusion strategy. To address the issue of class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is applied. A detailed simulation was carried out using a 1.5 MW three-bladed Wind Turbine model, employing tools such as Turbsim, FAST, and Matlab Simulink, to collect rotor speed data under different wind conditions. Mass imbalances were simulated by modifying blade density in the software. The fusion architecture combines feature extraction with Power Spectral Density analysis, improving the CNNs ability to work across both frequency and time domains. The effectiveness of this approach was confirmed through a comparative analysis with 9 classifiers and 4 different dataset combinations, demonstrating its capability in detecting mass imbalances.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"191-197"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879178","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparative study between deep learning approaches for aphid classification","authors":"Brenda Slongo Taca;Douglas Lau;Rafael Rieder","doi":"10.1109/TLA.2025.10879193","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879193","url":null,"abstract":"This study presents a performance comparison between two convolutional neural networks in the task of detecting aphids in digital images: AphidCV, customized for counting, classifying, and measuring aphids, and YOLOv8, state-of-the-art in real-time object detection. Our work considered 48,000 images for training for six different insect species (8,000 images divided into four classes), in addition to data augmentation techniques. For comparative purposes, we considered evaluation metrics available to both architectures (Accuracy, Precision, Recall, and F1-Score) and additional metrics (ROC Curve and PR AUC for AphidCV; mAP50 and mAP50-95 for YOLOv8). The results revealed an average F1-Score=0.891 for the AphidCV architecture, version 3.0, and an average F1-Score=0.882 for the YOLOv8, medium version, demonstrating the effectiveness of both architectures for training aphid detection models. Overall, AphidCV performed slightly better for the majority of metrics and species in the study, serving its design purpose very well. YOLOv8 proved to be faster to converge the models, with the potential to apply in research considering many aphid species.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"198-204"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879193","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Attack Optimization Supported Enhanced Deep Learning to Facilitate Power System Event Detection using PMU Data","authors":"Saba Kausar M Shaikh;Manjunath Kallamadi","doi":"10.1109/TLA.2025.10879175","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879175","url":null,"abstract":"Accurate event detection is crucial for initiating control and protection measures in power systems to ensure enhanced and reliable operation. Phasor measurement units (PMUs) play a vital role in various functional aspects of power systems, including state estimation and intelligent protection algorithms. However, the authenticity of real-time data from PMUs must be verified before feeding it into applicable real-time algorithms to prevent undesirable or erroneous operations. This paper aims to present an efficient preprocessing methodology for identifying unwanted, incorrect, missing, or noisy PMU data to facilitate robust event detection algorithms. The proposed methodology leverages real-time data-driven deep learning techniques for authenticating incoming data. Given the high sampling rate of PMUs, the presence of extraneous data can lead to false event detection, necessitating reliable data preprocessing. Challenges identified in existing literature, such as the limitations of Steady State (SS)-Local Outlier Factor (LOF) in event detection and classification, issues with detecting line tripping and inter-area oscillations, computational and bandwidth requirements for micro-PMU installations, and false alarms resulting from inaccuracies in frequency ramp rate determination, are addressed. To overcome these challenges, this research proposes a deep learning approach that utilizes modified Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) classifiers to classify and extract features from PMU data, enabling highly efficient detection of disturbances in transmission lines. Additionally, a hybrid attack optimization (HAO) technique is employed to enhance convergence rates, accuracy, and efficiency. Performance evaluation of the proposed system is conducted by calculating and assessing disturbances generated by power lines using metrics such as accuracy, precision, recall, System Average Interruption Duration Index (SAIDI), and System Average Interruption Frequency Index (SAIFI).","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"223-231"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879175","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic Review of Radio Wave Techniques for Indoor Positioning Systems","authors":"Emily Juliana Costa e Silva;Kaio Yukio Goncalves Vieira Guedes;Pedro Augusto Araújo da Silva de Almeida Nava Alves;Paulo Rogério de Almeida Ribeiro;Alex Oliveira Barradas Filho","doi":"10.1109/TLA.2025.10879196","DOIUrl":"https://doi.org/10.1109/TLA.2025.10879196","url":null,"abstract":"Indoor human positioning has become crucial for applications such as health monitoring, security surveillance, human pose identification and rescue operations. However, achieving reliable indoor human positioning is challenging due to numerous constraints.This paper aims to compare and analyze radio waves techniques and approaches for indoor positioning,providing a comprehensive review for human detection, positioning and activity recognition. A systematic review of the scientific literature and datasets was conducted. Four digital libraries, ACM Library Digital, IEEE Xplore, ScienceDirect and Spring Link were searched to identify results that met the selection criteria. A data extraction process was performed on the selected articles and datasets. The Parsifal platform was utilized to extract relevant information. After completing the systematic review, It was identified 26 eligible articles and extracted 11 methods for radio wave detection. The overview of indoor positioning system with radio waves was introduced. The most frequently mentioned tools in the articles for the capture stage were Radar Sensors, Wireless Sensor, and Antennas. For the processing stage, DNN Techniques, Processing Algorithms followed by Filtering, Fingerprint, Trilateration, and other machine learning algorithms formed the majority.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 3","pages":"205-215"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10879196","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}