Pub Date : 2025-11-07DOI: 10.1109/TLA.2025.11231217
Mauricio Morais Almeida;João Dallyson Sousa de Almeida;Geraldo Braz Junior;Aristofanes Correa Silva;Anselmo Cardoso de Paiva
Time series are widely used because they capture the relationship between events over time. However, when data is missing, this dependency is compromised. Traditional imputation techniques are being replaced by approaches based on neural networks, especially generative adversarial networks (GANs)and conditional generative adversarial networks (cGANs), due to their high capacity for reconstructing complex patterns.In this research, we explore an innovative path: transforming time series into images to recover missing data. We propose a new version of this transformation, incorporating two channels, trend and seasonality. We evaluated four generative architectures (CycleGAN, DCGAN, Pix2Pix, and DiscoGAN) in 240 models, covering different datasets and absence rates from 10% to 40%. We also introduced an unprecedented loss function to reduce the sensitivity of networks to anomalous data. The results show that the proposed two-channel approach produced the most stable imputations. Pix2Pix showed the best average performance: 75% of the Mean Absolute Percentage Error (MAPE) errors were below 0.21 (10% missing) and 2.66 (40% missing). For the Adapted Symmetric Mean Absolute Percentage Error (ASMAPE), the maximum third quartile values were 1.06 and 3.21, respectively. With the proposed loss function, the MAPE error fell from 12.95 to 3.21, and the ASMAPE from 2.86 to 2.66 in the best scenario, with a significant reduction that reinforces the effectiveness of the technique.
{"title":"Generative Learning for Imputation of Univariate Time Series Using Images and GANs","authors":"Mauricio Morais Almeida;João Dallyson Sousa de Almeida;Geraldo Braz Junior;Aristofanes Correa Silva;Anselmo Cardoso de Paiva","doi":"10.1109/TLA.2025.11231217","DOIUrl":"https://doi.org/10.1109/TLA.2025.11231217","url":null,"abstract":"Time series are widely used because they capture the relationship between events over time. However, when data is missing, this dependency is compromised. Traditional imputation techniques are being replaced by approaches based on neural networks, especially generative adversarial networks (GANs)and conditional generative adversarial networks (cGANs), due to their high capacity for reconstructing complex patterns.In this research, we explore an innovative path: transforming time series into images to recover missing data. We propose a new version of this transformation, incorporating two channels, trend and seasonality. We evaluated four generative architectures (CycleGAN, DCGAN, Pix2Pix, and DiscoGAN) in 240 models, covering different datasets and absence rates from 10% to 40%. We also introduced an unprecedented loss function to reduce the sensitivity of networks to anomalous data. The results show that the proposed two-channel approach produced the most stable imputations. Pix2Pix showed the best average performance: 75% of the Mean Absolute Percentage Error (MAPE) errors were below 0.21 (10% missing) and 2.66 (40% missing). For the Adapted Symmetric Mean Absolute Percentage Error (ASMAPE), the maximum third quartile values were 1.06 and 3.21, respectively. With the proposed loss function, the MAPE error fell from 12.95 to 3.21, and the ASMAPE from 2.86 to 2.66 in the best scenario, with a significant reduction that reinforces the effectiveness of the technique.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 12","pages":"1189-1200"},"PeriodicalIF":1.3,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11231217","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455997","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}
Pub Date : 2025-11-06DOI: 10.1109/TLA.2025.11231227
{"title":"Table of Contents December 2025","authors":"","doi":"10.1109/TLA.2025.11231227","DOIUrl":"https://doi.org/10.1109/TLA.2025.11231227","url":null,"abstract":"","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 12","pages":"1150-1151"},"PeriodicalIF":1.3,"publicationDate":"2025-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11231227","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449311","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}
Pub Date : 2025-10-07DOI: 10.1109/TLA.2025.11194775
Leonardo F. Dos Santos;Cícero Zanette;Elisa G. Vergamini;Lucca Maitan;Thiago Boaventura
This paper proposes a novel 3D graphical representation for impedance control, called the impedance space, to foster the analysis of the dynamic behavior of robotic compliant controllers. The method overcomes limitations of existing 2D graphical approaches by incorporating mass, stiffness, and damping dynamics, and associates the impedance control parameters with linear transformations to plot a parametric 3D ellipse and its projections in 2D for a mass-spring-damper impedance under sinusoidal reference. Experimental evaluation demonstrates the effectiveness of the proposed representation for analysis of impedance control. The method applies to various compliant control topologies and can be extended to other model-based control approaches.
{"title":"Impedance Space Method: Time-Independent Parametric Ellipses for Robot Compliant Control","authors":"Leonardo F. Dos Santos;Cícero Zanette;Elisa G. Vergamini;Lucca Maitan;Thiago Boaventura","doi":"10.1109/TLA.2025.11194775","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194775","url":null,"abstract":"This paper proposes a novel 3D graphical representation for impedance control, called the impedance space, to foster the analysis of the dynamic behavior of robotic compliant controllers. The method overcomes limitations of existing 2D graphical approaches by incorporating mass, stiffness, and damping dynamics, and associates the impedance control parameters with linear transformations to plot a parametric 3D ellipse and its projections in 2D for a mass-spring-damper impedance under sinusoidal reference. Experimental evaluation demonstrates the effectiveness of the proposed representation for analysis of impedance control. The method applies to various compliant control topologies and can be extended to other model-based control approaches.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"1081-1089"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194775","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236633","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}
Pub Date : 2025-10-07DOI: 10.1109/TLA.2025.11194778
Guilherme De Oliveira Alves;João Alberto Passos Filho
The increasing penetration of variable renewable energy sources, such as photovoltaic and wind power, poses significant challenges to the real-time security assessment of power systems. In this context, the Steady-State Security Regions framework has emerged as a robust tool for voltage security assessment, providing valuable insights into the steady-state operating limits of electrical networks. However, the computational burden associated with determining these regions during system operation remains a major obstacle for current methodologies. This paper presents a novel approach for efficiently identifying these regions using artificial neural networks, enabling the fast and accurate delineation of security boundaries suitable for real-time and near-real-time applications. The methodology was validated on the IEEE 9-Bus and New England test systems, achieving accuracy comparable to conventional techniques while reducing computational time by up to 96%. The results underscore the potential of the proposed method as a scalable and effective tool to support operational decision-making in power systems with high shares of renewable generation.
{"title":"A Novel Methodology for Determining Steady-State Security Regions Using Artificial Neural Networks in Near Real-Time Applications","authors":"Guilherme De Oliveira Alves;João Alberto Passos Filho","doi":"10.1109/TLA.2025.11194778","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194778","url":null,"abstract":"The increasing penetration of variable renewable energy sources, such as photovoltaic and wind power, poses significant challenges to the real-time security assessment of power systems. In this context, the Steady-State Security Regions framework has emerged as a robust tool for voltage security assessment, providing valuable insights into the steady-state operating limits of electrical networks. However, the computational burden associated with determining these regions during system operation remains a major obstacle for current methodologies. This paper presents a novel approach for efficiently identifying these regions using artificial neural networks, enabling the fast and accurate delineation of security boundaries suitable for real-time and near-real-time applications. The methodology was validated on the IEEE 9-Bus and New England test systems, achieving accuracy comparable to conventional techniques while reducing computational time by up to 96%. The results underscore the potential of the proposed method as a scalable and effective tool to support operational decision-making in power systems with high shares of renewable generation.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"1060-1069"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194778","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236703","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}
Pub Date : 2025-10-07DOI: 10.1109/TLA.2025.11194769
Raviteja P.;Narasimharaju B.L.;Naresh S.V.K.
A p-type modified quadratic gain buck-boost (PMQBB) converter is proposed in this paper. PMQBB converter topology evolution is based on the integration of a modified quadratic boost configuration with the p-type converter structure. Both of the inductors are in continuous conduction mode (CCM). The proposed PMQBB converters key features include a reduced component count, lower order, high voltage gain, and continuous input current. The proposed PMQBB converter exhibits a buck capability at a duty ratio lower or equal than 0.2929. This paper provides a comprehensive description of the PMQBB converter, including its steady-state analysis, operating modes, and analysis of semiconductor voltage and current stress. To emphasize the PMQBB converter, a detailed comparative study is presented. A 40/400 V, 300 W hardware prototype is tested to authenticate the converter's performance. The experimental outcomes validate the superior performance and efficiency of the PMQBB converter, highlighting its suitability for high-gain applications.
{"title":"A P-type Modified Quadratic Gain Buck-Boost Converter for DC Microgrids","authors":"Raviteja P.;Narasimharaju B.L.;Naresh S.V.K.","doi":"10.1109/TLA.2025.11194769","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194769","url":null,"abstract":"A p-type modified quadratic gain buck-boost (PMQBB) converter is proposed in this paper. PMQBB converter topology evolution is based on the integration of a modified quadratic boost configuration with the p-type converter structure. Both of the inductors are in continuous conduction mode (CCM). The proposed PMQBB converters key features include a reduced component count, lower order, high voltage gain, and continuous input current. The proposed PMQBB converter exhibits a buck capability at a duty ratio lower or equal than 0.2929. This paper provides a comprehensive description of the PMQBB converter, including its steady-state analysis, operating modes, and analysis of semiconductor voltage and current stress. To emphasize the PMQBB converter, a detailed comparative study is presented. A 40/400 V, 300 W hardware prototype is tested to authenticate the converter's performance. The experimental outcomes validate the superior performance and efficiency of the PMQBB converter, highlighting its suitability for high-gain applications.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"1036-1049"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194769","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236632","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}
This study presents a radio coverage analysis of the 4G LTE network operated by Ecuadors National Telecommunications Corporation (CNT) in Ambatos Historic Center, a dense urban area with complex topography. Over a seven day period, field measurements of the Reference Signal Received Power (RSRP) were collected along 13 primary and 19 secondary streets using two mobile devices on mid-range and one low equipped with the Network Cell Info Lite application. Both pedestrian and vehicular scenarios were evaluated, and compliance with the regulatory parameter SMA-QoS-9, established by Ecuadors Telecommunications Regulation and Control Agency (ARCOTEL), was assessed based on minimum power ( 100 dBm) and location coverage ( 95%). Results revealed that measured coverage fell below the regulatory threshold, with average compliance levels of 84.71% for pedestrian data and 76.77% for vehicular data, while simulated results based on official base station parameters reached 100% coverage. A 2.43 dB discrepancy in RSRP was observed between pedestrian and vehicular measurements, attributed to Doppler effects, signal obstruction, and multipath propagation. The proposed low-cost and accessible methodology is shown to be effective for in assessing real-world LTE performance, enabling operators and regulators to identify critical coverage gaps and calibrate network simulators. These findings support service improvement strategies and provide a foundation for efficient 5G NR deployment in similar urban environments.
本研究对厄瓜多尔国家电信公司（CNT）在Ambatos历史中心运营的4G LTE网络进行了无线电覆盖分析，这是一个地形复杂的密集城区。在7天的时间里，使用配备Network Cell Info Lite应用程序的两台中低端移动设备，沿着13条主要街道和19条次要街道收集了参考信号接收功率（RSRP）的现场测量数据。对行人和车辆场景进行了评估，并根据最小功率（100 dBm）和位置覆盖（95%）评估了厄瓜多尔电信监管和控制机构（ARCOTEL）制定的监管参数SMA-QoS-9的合规性。结果表明，实测覆盖率低于监管阈值，行人数据的平均符合率为84.71%，车辆数据的平均符合率为76.77%，而基于官方基站参数的模拟结果覆盖率为100%。由于多普勒效应、信号阻塞和多径传播，行人和车辆的RSRP测量值存在2.43 dB的差异。所提出的低成本和易于使用的方法被证明是评估实际LTE性能的有效方法，使运营商和监管机构能够识别关键的覆盖差距并校准网络模拟器。这些发现为服务改进策略提供了支持，并为在类似城市环境中高效部署5G NR提供了基础。
{"title":"Radio Coverage Analysis of a 4G Network in Ambato's Center","authors":"Bryan Manzano;Robert Rodríguez;David Moreno;Jefferson Ribadeneira","doi":"10.1109/TLA.2025.11194773","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194773","url":null,"abstract":"This study presents a radio coverage analysis of the 4G LTE network operated by Ecuadors National Telecommunications Corporation (CNT) in Ambatos Historic Center, a dense urban area with complex topography. Over a seven day period, field measurements of the Reference Signal Received Power (RSRP) were collected along 13 primary and 19 secondary streets using two mobile devices on mid-range and one low equipped with the Network Cell Info Lite application. Both pedestrian and vehicular scenarios were evaluated, and compliance with the regulatory parameter SMA-QoS-9, established by Ecuadors Telecommunications Regulation and Control Agency (ARCOTEL), was assessed based on minimum power ( 100 dBm) and location coverage ( 95%). Results revealed that measured coverage fell below the regulatory threshold, with average compliance levels of 84.71% for pedestrian data and 76.77% for vehicular data, while simulated results based on official base station parameters reached 100% coverage. A 2.43 dB discrepancy in RSRP was observed between pedestrian and vehicular measurements, attributed to Doppler effects, signal obstruction, and multipath propagation. The proposed low-cost and accessible methodology is shown to be effective for in assessing real-world LTE performance, enabling operators and regulators to identify critical coverage gaps and calibrate network simulators. These findings support service improvement strategies and provide a foundation for efficient 5G NR deployment in similar urban environments.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"1099-1108"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194773","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236672","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}
A flexible low-temperature plasma (LTP) source device was developed utilizing a radiofrequency (RF) generator coupled to a coaxial cable through a homemade L-shape matching network and a supple plastic hose that conveys a gas flow and shields the coaxial cable up to the reactors nozzle. The impedance matching network provides an electric power transfer of minimum of 94.11% operating under normal conditions. The LTP device arrangement is described, and later characterized via optical emission spectroscopy and electric power consumption. This procedure is essential to determine the adequate application of the generated plasma over heat-sensitive materials, primarily organic matter, to provide adequate information about its physicochemical activity. The produced LTP interacts with surrounding air particles, generating reactive oxygen and nitrogen species (RONS) that exhibit bactericidal and antiseptic properties due to their strong biochemical reactivity. The electromagnetic irradiation, ultraviolet (UV) emission, and thermal surface effect produced under normal working conditions of the LTP source device are safe to apply to heat-sensitive matter. The devices inactivation property was validated through qualitative deactivation trials of Escherichia coli and Enterococcus faecalis and quantitative deactivation trials of Escherichia coli. The device inactivated 99.996% of E. coli at a concentration of 3.6106 colony forming units per mL (CFU/mL) in 180 s at 16 W, this result corresponds to a 4.43-log10 reduction in E. coli viability.
{"title":"Flexible Low-Temperature RF Plasma Source for Biomedical Applications","authors":"Rosendo Peña-Eguiluz;Antonio Mercado-Cabrera;Alma Hernández-Arias;Benjamín Rodríguez-Méndez;Régulo López-Callejas;Raúl Valencia-Alvarado;Bethsabet Jaramillo-Sierra","doi":"10.1109/TLA.2025.11194766","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194766","url":null,"abstract":"A flexible low-temperature plasma (LTP) source device was developed utilizing a radiofrequency (RF) generator coupled to a coaxial cable through a homemade L-shape matching network and a supple plastic hose that conveys a gas flow and shields the coaxial cable up to the reactors nozzle. The impedance matching network provides an electric power transfer of minimum of 94.11% operating under normal conditions. The LTP device arrangement is described, and later characterized via optical emission spectroscopy and electric power consumption. This procedure is essential to determine the adequate application of the generated plasma over heat-sensitive materials, primarily organic matter, to provide adequate information about its physicochemical activity. The produced LTP interacts with surrounding air particles, generating reactive oxygen and nitrogen species (RONS) that exhibit bactericidal and antiseptic properties due to their strong biochemical reactivity. The electromagnetic irradiation, ultraviolet (UV) emission, and thermal surface effect produced under normal working conditions of the LTP source device are safe to apply to heat-sensitive matter. The devices inactivation property was validated through qualitative deactivation trials of Escherichia coli and Enterococcus faecalis and quantitative deactivation trials of Escherichia coli. The device inactivated 99.996% of E. coli at a concentration of 3.6106 colony forming units per mL (CFU/mL) in 180 s at 16 W, this result corresponds to a 4.43-log10 reduction in E. coli viability.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"1131-1142"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194766","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236681","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}
Pub Date : 2025-10-07DOI: 10.1109/TLA.2025.11194776
Julio Martins;Josue Lopez-Cabrejos;Quefren Leher;Thuanne Paixão;Ana Beatriz Alvarez;Facundo Palomino-Quispe
Printed circuit boards (PCBs) are key components in the electronics industry, and ensuring their integrity is essential for reliable manufacturing. Automated inspection systems based on computer vision, although efficient, face challenges. In this scenario, deep learning techniques have become effective solutions for detecting defects in more modern and complex PCBs. This article presents a comparative study between the YOLOv8n, YOLOv11n and RT-DETRv2 models for identifying defects in PCBs. The experiments were conducted using the PKU-Market-PCB dataset, which includes Missing Hole, Mouse Bite, Open Circuit, Short Circuit, Spur and Spurious Copper defects. To reduce the computational cost, modified versions of YOLOv8n and YOLOv11n with Depthwise convolution blocks (YOLOv8-DWConv and YOLOv11-DWConv). The analysis includes quantitative and qualitative comparisons. In addition, the robustness of the models is evaluated under challenging conditions with blur and illumination gradient noise. The results indicate that YOLOv11n achieves the best overall performance, while YOLOv11n-DWConv offers a competitive balance between precision and computational efficiency.
{"title":"Defect Detection in Printed Circuit Boards: A Comparative Analysis of Object Detection Models with Depthwise Convolution Adaptation","authors":"Julio Martins;Josue Lopez-Cabrejos;Quefren Leher;Thuanne Paixão;Ana Beatriz Alvarez;Facundo Palomino-Quispe","doi":"10.1109/TLA.2025.11194776","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194776","url":null,"abstract":"Printed circuit boards (PCBs) are key components in the electronics industry, and ensuring their integrity is essential for reliable manufacturing. Automated inspection systems based on computer vision, although efficient, face challenges. In this scenario, deep learning techniques have become effective solutions for detecting defects in more modern and complex PCBs. This article presents a comparative study between the YOLOv8n, YOLOv11n and RT-DETRv2 models for identifying defects in PCBs. The experiments were conducted using the PKU-Market-PCB dataset, which includes Missing Hole, Mouse Bite, Open Circuit, Short Circuit, Spur and Spurious Copper defects. To reduce the computational cost, modified versions of YOLOv8n and YOLOv11n with Depthwise convolution blocks (YOLOv8-DWConv and YOLOv11-DWConv). The analysis includes quantitative and qualitative comparisons. In addition, the robustness of the models is evaluated under challenging conditions with blur and illumination gradient noise. The results indicate that YOLOv11n achieves the best overall performance, while YOLOv11n-DWConv offers a competitive balance between precision and computational efficiency.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"1001-1010"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194776","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236683","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}
Pub Date : 2025-10-07DOI: 10.1109/TLA.2025.11194771
Diana Guadalupe Molina Bermúdez;José Antonio Vázquez López;Juan Israel Yañez Vargas;Claudia Alejandra Gallegos Sánchez
Metallic materials are composed of elements with defined chemical composition, and their intrinsic atomic arrangement confers them a distinctive crystalline structure. Thus, it is relevant to study of metallic materials, specifically cast aluminum alloys, whose physical and mechanical properties depend inherently on their chemical composition. Regarding the importance of mechanical properties, such as hardness, elastic modulus and ultimate tensile strength in optimizing industrial performance, it becomes essential to employ robust methods for their estimation. This study examines the computational estimation of mechanical properties from the chemical composition of various cast aluminum alloys. Two estimation modeling approaches were employed: Artificial Neural Networks (ANNs) and Multiple Linear Regression (MLR). Model performance was evaluated using three statistical metrics: Mean Absolute Error (MAE), which measures the average magnitude of errors; Root Mean Square Error (RMSE), which emphasizes larger error; and Mean Absolute Percentage Error (MAPE), which evaluates the percentage error relative to observed values. The results revealed that the ANN model exhibited superior estimation accuracy across all metrics when compared to the MLR approach. Specifically, the ANN model achieved lower values of MAE and RMSE, indicating more precise estimations and a significantly reduced MAPE, demonstrating improved reliability in estimating mechanical properties. These finding underscore the potential of ANNs as a more effective tool for estimating the mechanical performance of cast aluminum alloys based on their chemical composition. Additionally, the estimation capacity of both models was externally validated using experimental data reported in the literature, enhancing the reliability of the findings.
{"title":"Comparative Between Artificial Neural Networks and Multiple Linear Regression for the Estimation of Mechanical Properties in Cast Aluminum","authors":"Diana Guadalupe Molina Bermúdez;José Antonio Vázquez López;Juan Israel Yañez Vargas;Claudia Alejandra Gallegos Sánchez","doi":"10.1109/TLA.2025.11194771","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194771","url":null,"abstract":"Metallic materials are composed of elements with defined chemical composition, and their intrinsic atomic arrangement confers them a distinctive crystalline structure. Thus, it is relevant to study of metallic materials, specifically cast aluminum alloys, whose physical and mechanical properties depend inherently on their chemical composition. Regarding the importance of mechanical properties, such as hardness, elastic modulus and ultimate tensile strength in optimizing industrial performance, it becomes essential to employ robust methods for their estimation. This study examines the computational estimation of mechanical properties from the chemical composition of various cast aluminum alloys. Two estimation modeling approaches were employed: Artificial Neural Networks (ANNs) and Multiple Linear Regression (MLR). Model performance was evaluated using three statistical metrics: Mean Absolute Error (MAE), which measures the average magnitude of errors; Root Mean Square Error (RMSE), which emphasizes larger error; and Mean Absolute Percentage Error (MAPE), which evaluates the percentage error relative to observed values. The results revealed that the ANN model exhibited superior estimation accuracy across all metrics when compared to the MLR approach. Specifically, the ANN model achieved lower values of MAE and RMSE, indicating more precise estimations and a significantly reduced MAPE, demonstrating improved reliability in estimating mechanical properties. These finding underscore the potential of ANNs as a more effective tool for estimating the mechanical performance of cast aluminum alloys based on their chemical composition. Additionally, the estimation capacity of both models was externally validated using experimental data reported in the literature, enhancing the reliability of the findings.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"960-968"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194771","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236700","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}
Pub Date : 2025-10-07DOI: 10.1109/TLA.2025.11194762
Harigovindan V P;Deepa R;Goutham Veerapu
Underwater acoustic sensor networks (UASNs) support a variety of oceanic applications but suffer from limited communication bandwidth, reliability, and energy efficiency. Cooperative non-orthogonal multiple access (CNOMA) with simultaneous wireless information and power transfer (SWIPT) schemes are proposed for UASNs to meet these constraints. The unique characteristic of underwater acoustic channels compared to terrestrial wireless channels is the distance-dependent bandwidth, which provides additional bandwidth to the near user compared to the far user in NOMA-based UASNs. In this research work, we propose to enhance the performance of power splitting (PS) and time switching (TS) SWIPT schemes by utilizing this additional bandwidth at the near user in NOMA-based UASNs. We consider a CNOMA-based UASN and derive closed-form expressions for average achievable rates, energy efficiency, and outage probability with improved PS-SWIPT and TS-SWIPT schemes. From the analytical results, it is evident that the average achievable rate, energy efficiency and outage probability performances are significantly improved with the proposed methods. The analytical results are corroborated with extensive simulation studies.
{"title":"Performance Enhancement of SWIPT by Utilizing the Distance Dependent Bandwidth of Underwater Channel for Cooperative NOMA based UASNs","authors":"Harigovindan V P;Deepa R;Goutham Veerapu","doi":"10.1109/TLA.2025.11194762","DOIUrl":"https://doi.org/10.1109/TLA.2025.11194762","url":null,"abstract":"Underwater acoustic sensor networks (UASNs) support a variety of oceanic applications but suffer from limited communication bandwidth, reliability, and energy efficiency. Cooperative non-orthogonal multiple access (CNOMA) with simultaneous wireless information and power transfer (SWIPT) schemes are proposed for UASNs to meet these constraints. The unique characteristic of underwater acoustic channels compared to terrestrial wireless channels is the distance-dependent bandwidth, which provides additional bandwidth to the near user compared to the far user in NOMA-based UASNs. In this research work, we propose to enhance the performance of power splitting (PS) and time switching (TS) SWIPT schemes by utilizing this additional bandwidth at the near user in NOMA-based UASNs. We consider a CNOMA-based UASN and derive closed-form expressions for average achievable rates, energy efficiency, and outage probability with improved PS-SWIPT and TS-SWIPT schemes. From the analytical results, it is evident that the average achievable rate, energy efficiency and outage probability performances are significantly improved with the proposed methods. The analytical results are corroborated with extensive simulation studies.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 11","pages":"980-988"},"PeriodicalIF":1.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11194762","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236706","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：