Pub Date : 2024-01-23DOI: 10.1109/TLA.2024.10412029
Jose Enriquez;Jaime Cepeda;Oscar de Lima
This article describes the control scheme of an actual SCADA/EMS AGC (Automatic Generation Control) function and proposes a methodology for tuning the parameters of both generation units and AGC control systems. AGC tuning is split into two stages: unit control logic parameters and AGC system. In order to determine the optimal parameters, the application of a heuristic optimization algorithm, named MVMO (Mean-Variance Mapping Optimization), is proposed to solve a defined optimization problem. The proposed tuning methodology is validated using a realistic simulation environment named Operator Training Simulator (OTS). In addition, AGC system parameters are determined from real SCADA records and primary frequency response (PFR) obtained from frequency events recorded by the Ecuadorian WAMS (Wide Area Monitoring System). Finally, the AGC system is modeled in PowerFactory with the aim of achieving a realistic AGC model, considering a multimachine power system. For this aim, AGC control is implemented considering the realistic four-seconds sampling period related to a SCADA/EMS and the implementation of a filter that measures the rate of change of frequency (ROCOF) for allowing the primary frequency control to be previously performed. This model is then validated by simulations of generation outage events using a reduced model of the Ecuador-Colombia interconnected power system in PowerFactory.
{"title":"Dynamic Multimachine Modeling and Optimal Tuning of Automatic Generation Control","authors":"Jose Enriquez;Jaime Cepeda;Oscar de Lima","doi":"10.1109/TLA.2024.10412029","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412029","url":null,"abstract":"This article describes the control scheme of an actual SCADA/EMS AGC (Automatic Generation Control) function and proposes a methodology for tuning the parameters of both generation units and AGC control systems. AGC tuning is split into two stages: unit control logic parameters and AGC system. In order to determine the optimal parameters, the application of a heuristic optimization algorithm, named MVMO (Mean-Variance Mapping Optimization), is proposed to solve a defined optimization problem. The proposed tuning methodology is validated using a realistic simulation environment named Operator Training Simulator (OTS). In addition, AGC system parameters are determined from real SCADA records and primary frequency response (PFR) obtained from frequency events recorded by the Ecuadorian WAMS (Wide Area Monitoring System). Finally, the AGC system is modeled in PowerFactory with the aim of achieving a realistic AGC model, considering a multimachine power system. For this aim, AGC control is implemented considering the realistic four-seconds sampling period related to a SCADA/EMS and the implementation of a filter that measures the rate of change of frequency (ROCOF) for allowing the primary frequency control to be previously performed. This model is then validated by simulations of generation outage events using a reduced model of the Ecuador-Colombia interconnected power system in PowerFactory.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572683","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 : 2024-01-23DOI: 10.1109/TLA.2024.10412030
Maria Elisa Fernandes Octaviano;Eduardo Mendes Loureiro;Leandro Ramos de Araujo;Debora Rosana Ribeiro Penido de Araujo
This paper proposes a method for allocating and controlling batteries' state of charge in unbalanced distribution systems. Restrictions related to the depth of discharges and the relation between the nominal and operating capacity of the battery in relation to the operating temperature are proposed. The proposed optimization set is a mixed integer nonlinear with temporal coupling, so the genetic algorithm method was used with the quasi-static times series technique to solve the proposed problem. A simple technique to verify the economic feasibility of battery allocation using a k-factor is also proposed. The power flow equations were solved using OpenDSS. Several operational tests were accomplished using the IEEE34 Node Test Feeders. The results show that the consideration of deep discharge and operating temperature considerably impact the battery operating cycle and battery lifetime.
本文提出了一种在不平衡配电系统中分配和控制蓄电池充电状态的方法。提出了与放电深度有关的限制条件，以及电池的额定容量和工作温度下的工作容量之间的关系。提议的优化集是一个具有时间耦合的混合整数非线性问题，因此使用遗传算法方法和准静态时间序列技术来解决提议的问题。此外，还提出了一种使用 k 因子验证电池分配经济可行性的简单技术。使用 OpenDSS 解决了功率流方程。使用 IEEE34 节点测试馈线完成了多项运行测试。结果表明，深度放电和工作温度对电池的工作周期和使用寿命有很大影响。
{"title":"Battery Allocation and SOC in Distribution Systems Considering Temperature Constraints","authors":"Maria Elisa Fernandes Octaviano;Eduardo Mendes Loureiro;Leandro Ramos de Araujo;Debora Rosana Ribeiro Penido de Araujo","doi":"10.1109/TLA.2024.10412030","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412030","url":null,"abstract":"This paper proposes a method for allocating and controlling batteries' state of charge in unbalanced distribution systems. Restrictions related to the depth of discharges and the relation between the nominal and operating capacity of the battery in relation to the operating temperature are proposed. The proposed optimization set is a mixed integer nonlinear with temporal coupling, so the genetic algorithm method was used with the quasi-static times series technique to solve the proposed problem. A simple technique to verify the economic feasibility of battery allocation using a k-factor is also proposed. The power flow equations were solved using OpenDSS. Several operational tests were accomplished using the IEEE34 Node Test Feeders. The results show that the consideration of deep discharge and operating temperature considerably impact the battery operating cycle and battery lifetime.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412030","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572684","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 : 2024-01-23DOI: 10.1109/TLA.2024.10412034
Samuel Galvao Elias;Debora Cervieri Guterres;Robert Weingart Barreto;Helson Mario Martins do Vale
Genbank currently stands as one of the most significant global repositories of genetic information. However, despite its vast quantity and diversity of data, a considerable portion of the existing records suffer from disjointed and often lacking metadata, failing to provide the necessary context of their acquisition. In light of this, we propose GeneConnector, a tool that harnesses shared information among multiple records of the same specimen in Genbank, aiming to enhance the completeness of poorly annotated nodes across various information domains. To demonstrate the tools capabilities, we conducted a comprehensive review and aggregation of available data using the Genbank database of Genera of Phytopathogenic Fungi (GOPHY). Through our evaluation, we observed substantial gains in information by analyzing shared data among nodes connecting Genbank specimen records, resulting in impressive increments ranging from 2% to a remarkable 60%. Our approach empowers users to make precise, straightforward, and accurate assessments of the context associated to results, facilitated by two metrics that gauge the current level of data annotation and the potential information gain achievable following our evaluation.
{"title":"GeneConnector: Unlocking the full potential of Genbank metadata","authors":"Samuel Galvao Elias;Debora Cervieri Guterres;Robert Weingart Barreto;Helson Mario Martins do Vale","doi":"10.1109/TLA.2024.10412034","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412034","url":null,"abstract":"Genbank currently stands as one of the most significant global repositories of genetic information. However, despite its vast quantity and diversity of data, a considerable portion of the existing records suffer from disjointed and often lacking metadata, failing to provide the necessary context of their acquisition. In light of this, we propose GeneConnector, a tool that harnesses shared information among multiple records of the same specimen in Genbank, aiming to enhance the completeness of poorly annotated nodes across various information domains. To demonstrate the tools capabilities, we conducted a comprehensive review and aggregation of available data using the Genbank database of Genera of Phytopathogenic Fungi (GOPHY). Through our evaluation, we observed substantial gains in information by analyzing shared data among nodes connecting Genbank specimen records, resulting in impressive increments ranging from 2% to a remarkable 60%. Our approach empowers users to make precise, straightforward, and accurate assessments of the context associated to results, facilitated by two metrics that gauge the current level of data annotation and the potential information gain achievable following our evaluation.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572680","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 : 2024-01-23DOI: 10.1109/TLA.2024.10412036
Marcos Paulo de Oliveira Camargo;Gabriel dos Santos Pereira;Daniel Almeida;Leandro Apolinario Bento;William Fernande Dorante;Frank Jose Affonso
Cyber-Physical Systems (CPS) represent an evolution of embedded systems by the computational elements interacting with physical entities through a network. Self-adaptive Cyber-Physical Systems (Self-CPS) present specific features compared to traditional CPS because this type of system can deal with changes at runtime. In parallel, Reference Architectures (RA) enable reusable artifacts that aggregate the knowledge of software architectures in specific domains. RAs have facilitated the development, standardization, and system evolution in different domains. Despite their relevance, reference architectures that could support the more systematic development of Self-CPS, covering issues like self-protecting and observability, are not found yet. Based on this scenario, the main contribution of this paper is to present an RA for Self-CPS named RA4Self-CPS. The goal of this RA is to support the Self-CPS development that requires self-protecting, observability, and adaptation at runtime. To show the viability of our RA, we conducted a case study that revealed a good perspective to contribute to the Self-CPS area.
网络物理系统（CPS）是嵌入式系统的一种演变，其计算元素通过网络与物理实体进行交互。与传统的 CPS 相比，自适应网络物理系统（Self-CPS）具有特殊的功能，因为这类系统可以在运行时应对变化。与此同时，参考架构（RA）可实现可重复使用的工件，汇集特定领域的软件架构知识。参考架构促进了不同领域的开发、标准化和系统演进。尽管参考架构具有相关性，但目前还没有发现参考架构可以支持更系统地开发自携式计算机系统（Self-CPS），涵盖自我保护和可观测性等问题。基于这种情况，本文的主要贡献在于提出了一种名为 RA4Self-CPS 的自 CPS 参考架构。该 RA 的目标是支持需要运行时自我保护、可观察性和适应性的 Self-CPS 开发。为了证明我们的 RA 的可行性，我们进行了一项案例研究，为 Self-CPS 领域提供了一个很好的视角。
{"title":"RA4Self-CPS: A Reference Architecture for Self-adaptive Cyber-Physical Systems","authors":"Marcos Paulo de Oliveira Camargo;Gabriel dos Santos Pereira;Daniel Almeida;Leandro Apolinario Bento;William Fernande Dorante;Frank Jose Affonso","doi":"10.1109/TLA.2024.10412036","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412036","url":null,"abstract":"Cyber-Physical Systems (CPS) represent an evolution of embedded systems by the computational elements interacting with physical entities through a network. Self-adaptive Cyber-Physical Systems (Self-CPS) present specific features compared to traditional CPS because this type of system can deal with changes at runtime. In parallel, Reference Architectures (RA) enable reusable artifacts that aggregate the knowledge of software architectures in specific domains. RAs have facilitated the development, standardization, and system evolution in different domains. Despite their relevance, reference architectures that could support the more systematic development of Self-CPS, covering issues like self-protecting and observability, are not found yet. Based on this scenario, the main contribution of this paper is to present an RA for Self-CPS named RA4Self-CPS. The goal of this RA is to support the Self-CPS development that requires self-protecting, observability, and adaptation at runtime. To show the viability of our RA, we conducted a case study that revealed a good perspective to contribute to the Self-CPS area.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572682","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 : 2024-01-23DOI: 10.1109/TLA.2024.10412031
Erik Martinez-Vera;Pedro Banuelos-Sanchez
This paper comprehensively reviews bidirectional DC-DC converters and their control techniques for Electric Vehicle applications. A classification is proposed based on the three power ratings levels of the SAEJ1772 standard. Circuit topologies are compared based on power rating, switching frequency, static voltage gain, operating modes, number of components and power switch material. High switching-frequency topologies that include emerging Wide Bandgap (WBG) devices are also discussed. Cost comparison of traditional Si power switches and WBG devices employed in the reviewed topologies is also included. Traditional control methods for power converters in EVs are presented while also considering the emergence of Artificial Intelligence algorithms applied in systems controls that offer alternative methods to improve the efficiency of bidirectional DC-DC converters.
{"title":"Review of Bidirectional DC-DC Converters and Trends in Control Techniques for Applications in Electric Vehicles","authors":"Erik Martinez-Vera;Pedro Banuelos-Sanchez","doi":"10.1109/TLA.2024.10412031","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412031","url":null,"abstract":"This paper comprehensively reviews bidirectional DC-DC converters and their control techniques for Electric Vehicle applications. A classification is proposed based on the three power ratings levels of the SAEJ1772 standard. Circuit topologies are compared based on power rating, switching frequency, static voltage gain, operating modes, number of components and power switch material. High switching-frequency topologies that include emerging Wide Bandgap (WBG) devices are also discussed. Cost comparison of traditional Si power switches and WBG devices employed in the reviewed topologies is also included. Traditional control methods for power converters in EVs are presented while also considering the emergence of Artificial Intelligence algorithms applied in systems controls that offer alternative methods to improve the efficiency of bidirectional DC-DC converters.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572685","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 : 2024-01-23DOI: 10.1109/TLA.2024.10412028
{"title":"Table of Contents February 2024","authors":"","doi":"10.1109/TLA.2024.10412028","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412028","url":null,"abstract":"","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572677","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 paper is oriented to solve the output regulation problem for descriptor systems on the basis of the modified Francis equations, for arbitrary reference signals by means of High-Gain Observer as a dynamical model, where its outputs corresponds to the references to follow and the disturbances to reject involved in the regulation problem. In this way, the regulation of unmodeled but measurable reference signals is achieved. The sufficiency conditions for designing the regulator are given in this paper. Additionally, to establish a globally attractive mapping, Linear Matrix Inequalities are used to find the steady state in a straightforward manner. The nonlinear, non- minimum phase, and underactuated systems such as the Furuta Pendulum and Pendubot are used to illustrate the viability of the proposed approach. Finally, the controller implementation on the Furuta Pendulum is provided to demonstrate its performance in real-time applications.
{"title":"Output Regulation for Descriptor Systems with High-Gain Observer Used as Exosystem for Unmodeled References","authors":"Tonatiuh Hernandez-Cortes;Miguel Amador-Macias;Ricardo Tapia-Herrera;Jesus Meda-Campana","doi":"10.1109/TLA.2024.10412037","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412037","url":null,"abstract":"This paper is oriented to solve the output regulation problem for descriptor systems on the basis of the modified Francis equations, for arbitrary reference signals by means of High-Gain Observer as a dynamical model, where its outputs corresponds to the references to follow and the disturbances to reject involved in the regulation problem. In this way, the regulation of unmodeled but measurable reference signals is achieved. The sufficiency conditions for designing the regulator are given in this paper. Additionally, to establish a globally attractive mapping, Linear Matrix Inequalities are used to find the steady state in a straightforward manner. The nonlinear, non- minimum phase, and underactuated systems such as the Furuta Pendulum and Pendubot are used to illustrate the viability of the proposed approach. Finally, the controller implementation on the Furuta Pendulum is provided to demonstrate its performance in real-time applications.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412037","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572716","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 : 2024-01-23DOI: 10.1109/TLA.2024.10412038
Lucas Alves Torres;Andre Murilo;Renato Vilela Lopes;Vinicius Leal
This work investigates the utility and efficiency of simplified vehicle dynamics models in the Electronic Stability Control (ESC) context. The focus is not merely on the correlation between simplified and complex models but on the added value such models can bring to the automotive industry. By comparing the simplified models based on bicycle representation with a high-fidelity VI-CarRealTime (VI-CRT) model, this paper demonstrates that the simplified models have good correlation and offer computational advantages. This approach addresses the key dynamics essential for ESC and considers a generic sedan vehicle model to simulate standard maneuvers widely performed by the automotive industry. All the proposed models are nonlinear and include tire modeling based on the Magic Formula, with parameters derived from experimental tests. The paper also introduces a methodology for parameter optimization, enhancing the model's accuracy and reliability. The results indicate that the simplified models can be a viable alternative for specific applications such as control strategy tuning, rapid prototyping, and early-stage development. This work aims to fill the gap in the literature concerning the practical applicability and limitations of simplified vehicle dynamics models, thereby making a significant contribution to the field.
{"title":"Analysis and Virtual Validation of Vehicle Dynamics Models for Electronic Stability Control","authors":"Lucas Alves Torres;Andre Murilo;Renato Vilela Lopes;Vinicius Leal","doi":"10.1109/TLA.2024.10412038","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412038","url":null,"abstract":"This work investigates the utility and efficiency of simplified vehicle dynamics models in the Electronic Stability Control (ESC) context. The focus is not merely on the correlation between simplified and complex models but on the added value such models can bring to the automotive industry. By comparing the simplified models based on bicycle representation with a high-fidelity VI-CarRealTime (VI-CRT) model, this paper demonstrates that the simplified models have good correlation and offer computational advantages. This approach addresses the key dynamics essential for ESC and considers a generic sedan vehicle model to simulate standard maneuvers widely performed by the automotive industry. All the proposed models are nonlinear and include tire modeling based on the Magic Formula, with parameters derived from experimental tests. The paper also introduces a methodology for parameter optimization, enhancing the model's accuracy and reliability. The results indicate that the simplified models can be a viable alternative for specific applications such as control strategy tuning, rapid prototyping, and early-stage development. This work aims to fill the gap in the literature concerning the practical applicability and limitations of simplified vehicle dynamics models, thereby making a significant contribution to the field.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139573229","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 : 2024-01-23DOI: 10.1109/TLA.2024.10412035
Jiangfeng Bi;Haiyue Wei;Guoxin Zhang;Kuihe Yang;Ziying Song
In the realm of autonomous driving, LiDAR and camera sensors play an indispensable role, furnishing pivotal observational data for the critical task of precise 3D object detection. Existing fusion algorithms effectively utilize the complementary data from both sensors. However, these methods typically concatenate the raw point cloud data and pixel-level image features, unfortunately, a process that introduces errors and results in the loss of critical information embedded in each modality. To mitigate the problem of lost feature information, this paper proposes a Cross-Attention Dynamic Fusion (CADF) strategy that dynamically fuses the two heterogeneous data sources. In addition, we acknowledge the issue of insufficient data augmentation for these two diverse modalities. To combat this, we propose a Synchronous Data Augmentation (SDA) strategy designed to enhance training efficiency. We have tested our method using the KITTI and nuScenes datasets, and the results have been promising. Remarkably, our top-performing model attained an 82.52% mAP on the KITTI test benchmark, outperforming other state-of-the-art methods.
{"title":"DyFusion: Cross-Attention 3D Object Detection with Dynamic Fusion","authors":"Jiangfeng Bi;Haiyue Wei;Guoxin Zhang;Kuihe Yang;Ziying Song","doi":"10.1109/TLA.2024.10412035","DOIUrl":"https://doi.org/10.1109/TLA.2024.10412035","url":null,"abstract":"In the realm of autonomous driving, LiDAR and camera sensors play an indispensable role, furnishing pivotal observational data for the critical task of precise 3D object detection. Existing fusion algorithms effectively utilize the complementary data from both sensors. However, these methods typically concatenate the raw point cloud data and pixel-level image features, unfortunately, a process that introduces errors and results in the loss of critical information embedded in each modality. To mitigate the problem of lost feature information, this paper proposes a Cross-Attention Dynamic Fusion (CADF) strategy that dynamically fuses the two heterogeneous data sources. In addition, we acknowledge the issue of insufficient data augmentation for these two diverse modalities. To combat this, we propose a Synchronous Data Augmentation (SDA) strategy designed to enhance training efficiency. We have tested our method using the KITTI and nuScenes datasets, and the results have been promising. Remarkably, our top-performing model attained an 82.52% mAP on the KITTI test benchmark, outperforming other state-of-the-art methods.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412035","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139572681","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 : 2023-12-28DOI: 10.1109/TLA.2024.10375733
María Auxilio Medina Nieto;Eduardo López Domínguez;Jorge De la Calleja Mora;Yesenia Hernández Velázquez;Delia Arrieta Díaz
Annually, in Mexico, the National Institute of Statistics and Geography publishes a dataset called Module on Cyberbullying (MOCIBA). The article presents the evaluation of the quality of data collected in 2021 based on the ISO/IEC 25012 standard with the aim of promoting the reuse of public information distributed as open data. A mixed methodology of search and review of the dataset, its 277 catalogs, data dictionary, questionnaire, report of main results and metadata was implemented. The results are: semantic accuracy (99%), syntactic accuracy (100%), completeness (96%), consistency (100%), credibility (100%), timeliness (100%), accessibility (100%), conformity (100%), precision (100%), comprehensibility (93%), efficiency (60%), availability (100%) and portability (100%). Subsequently, an ontology written in Spanish language is described, this formally represents the concepts and their relationships from the documents of MOCIBA 2021.
{"title":"Quality Assessment and Semantic Representation of the Module on Cyberbullying","authors":"María Auxilio Medina Nieto;Eduardo López Domínguez;Jorge De la Calleja Mora;Yesenia Hernández Velázquez;Delia Arrieta Díaz","doi":"10.1109/TLA.2024.10375733","DOIUrl":"https://doi.org/10.1109/TLA.2024.10375733","url":null,"abstract":"Annually, in Mexico, the National Institute of Statistics and Geography publishes a dataset called Module on Cyberbullying (MOCIBA). The article presents the evaluation of the quality of data collected in 2021 based on the ISO/IEC 25012 standard with the aim of promoting the reuse of public information distributed as open data. A mixed methodology of search and review of the dataset, its 277 catalogs, data dictionary, questionnaire, report of main results and metadata was implemented. The results are: semantic accuracy (99%), syntactic accuracy (100%), completeness (96%), consistency (100%), credibility (100%), timeliness (100%), accessibility (100%), conformity (100%), precision (100%), comprehensibility (93%), efficiency (60%), availability (100%) and portability (100%). Subsequently, an ontology written in Spanish language is described, this formally represents the concepts and their relationships from the documents of MOCIBA 2021.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375733","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139060175","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：