IEEE Latin America Transactions最新文献

Denoising of EEG Signals in BrainComputer Interfaces Using Extended Kalman-Filtered Recurrent High-Order Neural Networks 基于扩展卡尔曼滤波递归高阶神经网络的脑机接口脑电信号去噪

IF 1.6 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-09-01 Epub Date: 2026-09-28 DOI: 10.1109/TLA.2026.11710329

Enrique López-Estrada;Jesus Alfonso Medrano-Hermosillo;Juan Alberto Ramírez-Quintana;Ivan Ramon Urbina Leos;Oscar Javier Suárez Sierra;Francisco-Ronay López-Estrada

引用次数: 0

Comparison of Tree-Based Machine Learning Models for Classification of Tuberculosis Outcomes in Brazil 基于树的机器学习模型在巴西结核病结果分类的比较

IF 1.6 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-09-01 Epub Date: 2026-09-25 DOI: 10.1109/TLA.2026.11710328

Heloísa de Almeida Pereira;Marcos Roberto Ribeiro;Ciniro Aparecido Leite Nametala

{"title":"Comparison of Tree-Based Machine Learning Models for Classification of Tuberculosis Outcomes in Brazil","authors":"Heloísa de Almeida Pereira;Marcos Roberto Ribeiro;Ciniro Aparecido Leite Nametala","doi":"10.1109/TLA.2026.11710328","DOIUrl":"https://doi.org/10.1109/TLA.2026.11710328","url":null,"abstract":"Tuberculosis remains a significant public health concern, recognized as a reemerging disease strongly associated with socioeconomic conditions. According to the World Health Organization, tuberculosis continues to be the leading cause of death from a single infectious agent worldwide in 2025. This study evaluates Random Forest, XGBoost, CatBoost, and LightGBM for classifying four treatment outcomes (cure, abandonment, death from tuberculosis, and death from other causes) using 53,656 epidemiological records from Minas Gerais, Brazil (20102024). A preprocessing pipeline was designed to handle heterogeneous and high-cardinality variables. Models were assessed with and without SMOTE balancing under 5-fold stratified cross-validation, using accuracy, weighted F1-score, and per-class recall as evaluation metrics. Without balancing, all models achieved approximately 0.75 accuracy but failed to detect minority outcomes. Experiments across multiple random seeds, feature subset analysis, and temporal validation were conducted to assess model robustness. With SMOTE, CatBoost achieved the best overall performance, with the highest cross-validation F1-score (0.7071 0.0034) and improved recall for abandonment and death outcomes. Results indicate that the combination of clinical and socioeconomic features is essential for predictive performance, and that data quality and class imbalance are the main obstacles to reliable minority-class detection in tuberculosis surveillance.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"24 9","pages":"981-995"},"PeriodicalIF":1.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11710328","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149033867","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}

引用次数: 0

Single and Multiple Open-Switch Fault Diagnosis in Electric Drives via Zero-Current Interval Analysis 基于零电流区间分析的电力传动单开、多开故障诊断

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421261

Luis Esteban Venghi;Facundo Aguilera;Pablo de la Barrera;Cristian De Angelo

引用次数: 0

Hybrid MDSOGIROGI Control Strategy for Mitigating Harmonics and Unbalance in SEIG Based Standalone Systems 基于SEIG的独立系统谐波和不平衡抑制的混合MDSOGIROGI控制策略

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421256

Jotirmoy Samanta;Ralli Sangno;Rajen Pudur;Yatindra Gopal;Julio C. Rosas-Caro

{"title":"Hybrid MDSOGIROGI Control Strategy for Mitigating Harmonics and Unbalance in SEIG Based Standalone Systems","authors":"Jotirmoy Samanta;Ralli Sangno;Rajen Pudur;Yatindra Gopal;Julio C. Rosas-Caro","doi":"10.1109/TLA.2026.11421256","DOIUrl":"https://doi.org/10.1109/TLA.2026.11421256","url":null,"abstract":"The self-excited induction generator (SEIG) is a promising machine for standalone, off-grid systems. However, this machine experiences multiple power quality issues (PQIs) when subjected to varying loads, particularly degradation in terminal voltage and frequency as the load increases. This paper presents a PQI mitigation technique using a shunt active power filter (SAPF) to regulate the terminal voltage of the SEIG and reduce the total harmonic distortion (THD) of the system, while maintaining power factor (PF) close to unity. A modified dual second-order generalised integrator (MDSOGI) is combined with a reduced-order generalised integrator (ROGI) to generate the reference current for controlling the SAPF. The terminal voltage of SEIG is regulated under dynamic load changes. Total harmonics distortion (THD) is reduced below 5% according to the IEEE 519-2022 standard. Furthermore, under an unbalanced load condition, the system becomes balanced after compensation with the SAPF. The experiment is conducted on a real-time platform using Opal-RT (OP4510), and the results of dynamic load changes are presented.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"24 3","pages":"307-318"},"PeriodicalIF":1.3,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421256","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147352559","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}

引用次数: 0

Mobile App for Tuberculosis Detection Using Deep Learning and NLP-Based Recommendations 使用深度学习和基于nlp的推荐的结核病检测移动应用程序

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421255

Camily Bravo-Flores;Derik Aranda-Neira;Wilmer Rivas-Asanza;Bertha Mazon-Olivo

{"title":"Mobile App for Tuberculosis Detection Using Deep Learning and NLP-Based Recommendations","authors":"Camily Bravo-Flores;Derik Aranda-Neira;Wilmer Rivas-Asanza;Bertha Mazon-Olivo","doi":"10.1109/TLA.2026.11421255","DOIUrl":"https://doi.org/10.1109/TLA.2026.11421255","url":null,"abstract":"Tuberculosis remains one of the leading causes of mortality from infectious diseases and conventional diagnostic methods are often limited by subjectivity. This study presents a mobile application for automated tuberculosis diagnosis, integrating a convolutional neural network (CNN) for chest X-ray classification with a natural language processing (NLP) module for clinical recommendations. Three CNN architectures were evaluated (DenseNet121, ResNet50, and MobileNetV2) using the CRISP-DM methodology, with a Kaggle dataset. DenseNet121 achieved the most balanced performance (Accuracy = 96.2%, Recall = 95.5%, F1-score = 96.2%), prioritizing the reduction of false positives and negatives. The model was integrated into a mobile application developed under the Extreme Programming methodology, employing a client-server architecture with RESTful APIs. The NLP component, based on the DeepSeek-R1 model through the OpenRouter platform, generated contextually relevant clinically responses. Validation with healthcare professionals showed that 91.7% would recommend it as a support tool for tuberculosis diagnosis, due to its diagnostic reliability, usability, and clinical recommendations. These findings confirm the clinical viability and practical utility of the application, positioning it as a valuable resource in healthcare contexts with limited specialist availability","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"24 3","pages":"227-238"},"PeriodicalIF":1.3,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421255","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147352569","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}

引用次数: 0

Path Planning using a One-shot-sampling Skeleton Map 使用一次性采样骨架图的路径规划

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421258

Gabriel O. Flores-Aquino;Octavio Gutierrez-Frias;Juan Irving Vasquez

{"title":"Path Planning using a One-shot-sampling Skeleton Map","authors":"Gabriel O. Flores-Aquino;Octavio Gutierrez-Frias;Juan Irving Vasquez","doi":"10.1109/TLA.2026.11421258","DOIUrl":"https://doi.org/10.1109/TLA.2026.11421258","url":null,"abstract":"Path planning algorithms fundamentally aim to compute collision-free paths, with many works focusing on finding the optimal distance path. However, for several applications, a more suitable approach is to balance response time, path safety, and path length. In this context, a skeleton map is a useful tool in graph-based schemes, as it provides an intrinsic representation of the free workspace. However, standard skeletonization algorithms are computationally expensive, as they are primarly oriented towards image processing tasks. We propose an efficient path-planning methodology that finds safe paths within an acceptable processing time. This methodology leverages a Deep Denoising Autoencoder (DDAE) based on the U-Net architecture to compute a skeletonized version of the navigation map, which we refer to as SkelUnet. The SkelUnet network facilitates exploration of the entire workspace through one-shot sampling (OSS), as opposed to the iterative or probabilistic sampling used by previous algorithms. SkelUnet is trained and tested on a dataset consisting of 12,500 two-dimensional dungeon maps. The motion planning methodology is evaluated in a simulation environment with an Unmanned Aerial Vehicle (UAV) in 250 previously unseen maps and assessed using several navigation metrics to quantify the navigability of the computed paths. The results demonstrate that using SkelUnet to construct the roadmap offers significant advantages, such as connecting all regions of free workspace, providing safer paths, and reducing processing time. These characteristics make this method particularly suitable for mobile robots in structured environments.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"24 3","pages":"260-268"},"PeriodicalIF":1.3,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421258","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147352531","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}

引用次数: 0

Assessment of Virtual Reality and Metaverse Applications in Higher Education 虚拟现实与虚拟世界在高等教育中的应用评估

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421168

Jose Joskowicz;Fabricio Gonzalez;Ines Urrestarazú;Lucia Tafernaberry

引用次数: 0

A Capacitor Coupled On-board Bi-directional Vehicle-to-Vehicle Charging System 电容耦合车载双向车对车充电系统

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421260

Mounika Reddimalla;Srinivasan Pradabane

{"title":"A Capacitor Coupled On-board Bi-directional Vehicle-to-Vehicle Charging System","authors":"Mounika Reddimalla;Srinivasan Pradabane","doi":"10.1109/TLA.2026.11421260","DOIUrl":"https://doi.org/10.1109/TLA.2026.11421260","url":null,"abstract":"In recent times, Vehicle-to-Vehicle (V2V) chargers have gained popularity to transfer the energy between two Electric Vehicles (EV). In this paper, a new direct V2V charger is proposed that uses a capacitor coupling and an on-board DC-DC converter in each EV to enable the energy transfer between them. Importantly, this charger differentiates itself from other V2V chargers by eliminating the requirement for motor winding and inverter circuit from an EV. The charger operation is verified through simulation studies (via MATLAB/Simulink) in three operating modes: Forward Boost, Reverse Buck and Forward Buck-Boost mode for EVs with battery voltage of 350 V and 450 V. The simulation studies are validated through the OPAL-RT Real-Time simulator. The proposed charger achieves an efficiency of 96.57 % in the forward boost mode, 96.56 % in the reverse buck mode, and 96.26 % in the forward buckboost mode of operation at a rated power level of 20 kW, while demonstrating a 25 % to 76 % reduction in component count compared to existing topologies. Further, a laboratory proof of concept is developed and tested with battery voltages of 12 V and 25.6 V in all modes of operation. Experimental results under static and dynamic discharge currents are presented.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"24 3","pages":"289-306"},"PeriodicalIF":1.3,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421260","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147352488","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}

引用次数: 0

Constrained model-based control for robust operation of a solid oxide fuel cell 固体氧化物燃料电池鲁棒运行的约束模型控制

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421257

Silvina Biagiola;Christian Schmidt;Jose Luis Figueroa

{"title":"Constrained model-based control for robust operation of a solid oxide fuel cell","authors":"Silvina Biagiola;Christian Schmidt;Jose Luis Figueroa","doi":"10.1109/TLA.2026.11421257","DOIUrl":"https://doi.org/10.1109/TLA.2026.11421257","url":null,"abstract":"Over the years, the Solid Oxide Fuel Cell (SOFC) has grown in popularity due to its high efficiency and fuel flexibility, low maintenance requirements and environmentally friendly features. Its durability and performance can be substantially enhanced through the implementation of optimal control strategies. However, controlling the SOFC is challenging due to its nonlinear behavior and the need to manage its operational constraints simultaneously. To come up with an effective control algorithm for a SOFC, it is necessary to understand its dynamic behavior. In this work, a Wiener model is developed for control purpose. This mathematical representation enables the use of an identification algorithm to estimate unknown parameters. Furthermore, the control-oriented model uncertainty is characterized and incorporated as bounds on the model parameters. The resulting model is integrated into a Model Predictive Control (MPC) framework, designed for both regulation and optimization objectives. This control scheme ensures robust constraint satisfaction for the whole set of characterized uncertain models. The simulation results show the benefits of the proposed model-based controller both for SOFC operation and performance enhancement.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"24 3","pages":"319-326"},"PeriodicalIF":1.3,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421257","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147352561","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}

引用次数: 0

Table of Contents March 2026 目录2026年3月

IF 1.3 4区工程技术

IEEE Latin America Transactions Pub Date : 2026-03-04 DOI: 10.1109/TLA.2026.11421254

引用次数: 0