检索结果-内蒙古大学图书馆

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Roberto Douglas Guimaraes de Aquino Joniel Bastos Barreto Aline Do Nascimento Rodrigues Filipe Alves Neto Verri Carlos Henrique Quartucci Forster PPG Operation Research Technological Institute of Aeronautics (ITA) Sao Jose dos Campos SP Brazil PPG Electronic and Computer Eng. ITA Sao Jose dos Campos SP Brazil Computer Science Division ITA Sao Jose dos Campos SP Brazil

The use of Unmanned Aerial Vehicles (UAVs)equipped with classification systems in Search and Rescue missions has increasingly shown great application potential. There are however pratical concerns regarding limited embedded computing power and adapting the classifier performance to the characteristics of a specific mission. The UAVs may acquire a large number of images during a mission and it is difficult for humans to search throughout this material. For this matter, we study the performance of a leaner Convolutional Neural Network model to select images with salient objects and present a tool that can help in decision making regarding the definition of the classification threshold through the analysis of possible operational impacts and consequences of eventual detection errors. We also show that, in this application, Data Augmentation is important to improve the classifier performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differential Linear Matrix Inequalities in Optimal and Robust Sampled-Data Filtering

引用

IFAC-PapersOnLine 2023年第2期56卷 9806-9811页

作者： Henrique W.R. Pereira Gabriela W. Gabriel André M. de Oliveira José C. Geromel Electronic Engineering Division ITA São José dos Campos SP Brazil Institute of Science and Technology UNIFESP São José dos Campos SP Brazil School of Electrical and Computer Engineering UNICAMP Campinas SP Brazil

This paper tackles the design of a robust filter for sampled-data linear time-invariant systems subject to parameter uncertainties. After the optimal solution is obtained, the two major classes of parameter uncertainty are considered, namely, convex bounded and norm bounded. For each of them, the filter associated to the minimum H2 guaranteed performance is determined. The design conditions are expressed through differential linear matrix inequalities (DLMIs), a mathematical device well adapted to cope with sampled-data systems because it naturally avoids matrix exponential and similar mappings. In this framework, the optimal nominal filter is determined, and it is shown that it exhibits a time-invariant observer-based structure. Illustrative examples are presented and discussed in order to put in clear evidence the theoretical results.

关键词： Sampled-data filtering robust estimation convex optimization observer design

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Intelligent Packet Filtering in Single-board Mini-computer Devices

Performance Evaluation of Intelligent Packet Filtering in Si...

引用

Brazilian Symposium on Computing System Engineering (SBESC)

作者： Rafael C Silva Fabio A Melo Mauri Aparecido de Oliveira Aldri Luiz dos Santos Lourenco Alves Pereira Division of Computer Science Aeronautics Institute of Technology Sao Jose dos Campos SP Brazil Department of Computer Science Federal University of Minas Gerais Belo Horizonte MG Brazil

The growth of IoT devices and the spread of remote Internet access technologies allow the emergence of several applications. As the connectivity areas expand and technologies evolve, so do the systems and devices that support its infrastructure. However, with the increase in its benefits, we can raise several concerns about network security. In this scenario, most devices have limited hardware resources and opaque security systems. Therefore, in this study, we implement and analyze the performance of a lightweight machine learning-based Network Intrusion Detection System. We adopted the AB-TRAP, which is a framework that enables the use of updated datasets and considers operational conditions, on a Raspberry Pi 4 device, evaluating the device’s CPU, memory, and network performance. The results showed an average CPU usage between 20% and 30%, and no memory overload for the NIDS implementation. Ultimately, the experiment results indicate that the framework implementation is suitable for the chosen device and that the lightweight detection system is viable. Additionally, we created a malicious traffic generation tool, which was used to generate the traffic used in the experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Firmware Based on Real-Time Operating System for Small Size League Robot

Implementation of Firmware Based on Real-Time Operating Syst...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Andrei Freiberger Marcos R. O. A. Maximo Denis Loubach Autonomous Computational Systems Lab São José Dos Campos SP Brazil Autonomous Computational Systems Lab Aeronautics Institute of Technology São José dos Campos SP Brazil Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

This article presents the implementation of a real-time operating system (RTOS) on ITAndroids Small Size League (SSL) category robots, a significant advancement for the team's participation in the Robocup SSL. The transition to using the STM32H753BI microcontroller and FreeRTOS on the second-generation Mainboard enhances temporal predictability and de-terminism, crucial for real-time systems. This development allows more efficient task management, including motor control, kicker charging, telemetry transmission, and fault handling, leading to improved robot performance and reliability during matches. The detailed system description and task implementation showcase how the Mainboard efficiently handles various functions such as motor control in a constant rate, responsive kicking mechanisms, and real-time telemetry collection and transmission. The work contributes by proposing a real-time operating system for a robot designed to participate in the RoboCup Small Size League (SSL). Despite the implementation being dependent on our team's design decisions, the concepts presented here can be adapted by other teams.

关键词： Motor drives Operating systems System performance Motors Real-time systems Hardware Telemetry Voltage control Robots Tuning

来源：评论

学校读者我要写书评

暂无评论

Improved Defensive Strategy in RoboCup Small Size League using Deep Reinforcement Learning

Improved Defensive Strategy in RoboCup Small Size League usi...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Adrisson R. Samersla Marcos R. O. A. Maximo Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division (IEC) Aeronautics Institute of Technology (ITA) São José dos Campos Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

The Small Size League (SSL) is one of the old-est leagues in RoboCup, an international scientific initiative whose objective is to advance the state-of-the-art in robotics. The matches are highly dynamic and competitive, an excellent environment to exercise and extend the latest decision-making techniques. In this work, we focus on the planning problem of the defense strategy in the SSL context. Our contribution lies in proposing a method for learning such behaviors using Deep Reinforcement Learning (DRL) algorithms. Through this technique, we intend to apply a more automated process than manually adjusting the heuristics used to handcraft such skills in code. For this purpose, the RoboCup Small Size League standard simulator grSim was adapted in order to implement a synchronous mode. Furthermore, we integrated this new simulator with ITAndroids team's code base and with the DRL algorithms provided by the Stable Baselines 3 library. With this setup, we successfully trained an agent using Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC), the state-of-the-art for continuous control reinforcement learning algorithms. Moreover, we demonstrate that the resulting policies outperform the hand-coded counterparts, showing potential to improve the team's overall defense strategy.

关键词： Codes Deep reinforcement learning Libraries Planning Reliability Robots Standards Optimization Sports Overfitting

来源：评论

学校读者我要写书评

暂无评论

Applying STAMP to Support the Synthesis of Controller Logic considering Safety Concerns 10

Applying STAMP to Support the Synthesis of Controller Logic ...

引用

10th Latin-American Symposium on Dependable Computing, LADC 2021

作者： Horta, Braulio Marques De Melo Bezerra, Juliana Hirata, Celso Massaki Research and Technology EMBRAER S.A Sao Jose dos Campos Brazil Instituto Tecnologico de Aeronautica-ITA Computer Science Department Sao Jose dos Campos Brazil

ISBN: (纸本)9781665478311

Controllers are key components of safety-critical systems. They are responsible for ensuring many of the system requirements through monitoring and action over other components the traditional approach for designing controllers encompasses careful understanding, analysis, and manual definition of the behavior of the controller. We propose a correct-by-construction method to synthesize the logic of controllers, based on supervisory control theory. In this paper, we focus on using STAMP to support the controller synthesis. STAMP is an accident causation model based on systems theory, which treats accidents and unacceptable losses as a dynamic control problem. Here STAMP aids to capture the system description, supporting the steps related to the definition of components and their interfaces, the specification of components' behavior, the identification of assumptions, and the determination of functional and safety properties. We provide an overview of the method, contextualizing the methods steps with the system of an automatic door. Later, we present a real system of a Nuclear Power Plant and discuss its outcomes. © 2021 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Sintering and Characterization of Ceramic Capacitor Based on BSZT for Use in Nonlinear Transmission Lines

Sintering and Characterization of Ceramic Capacitor Based on...

引用

2022 IEEE International Power Modulator and High Voltage Conference, IPMHVC 2022

作者： Neto, Lauro P. S. Aredes, Rangel. G. Antonelli, E. Rossi, Jose O. Lima, Gustavo N. Barroso, Joaquim J. Rangel, Elizete G. L. Schamiloglu, Edl Federal University of Sao Paulo Unifesp Sõo José Dos Campos Science and Technology Department Brazil National Institute for Space Research-INPE Sóo José Dos Campos Associated Plasma Laboratory Brazil University of New Mexico Albuquerque Electrical and Computer Engineering Department United States

ISBN: (纸本)9781665471657

Nonlinear transmission lines -NLTLs are promising as a high-power RF source in radars, battlefield communication disruption, satellites, biomedical instrumentation, and other communication systems [1-2]. Another way to produce the RF signals on NLTL is using nonlinear components such as ceramic capacitors. In this work, we synthesized and characterized a barium zirconium titanate ceramic for use in nonlinear dielectrics. Its application is in NLTLs due to their high permittivity > 5000 in the phase temperature transition with low tangent loss © 2022 IEEE.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems

arXiv

引用

arXiv 2023年

作者： Chizari, Nikzad Shoeibi, Niloufar Moreno-García, María N. Department of Computer Science and Automation Faculty of Sciences University of Salamanca Plaza de los Caídos sn Salamanca37008 Spain

Recommender Systems (RSs) are used to provide users with personalized item recommendations and help them overcome the problem of information overload. Currently, recommendation methods based on deep learning are gaining ground over traditional methods such as matrix factorization due to their ability to represent the complex relationships between users and items and to incorporate additional information. The fact that these data have a graph structure and the greater capability of Graph Neural Networks (GNNs) to learn from these structures has led to their successful incorporation into recommender systems. However, the bias amplification issue needs to be investigated while using these algorithms. Bias results in unfair decisions, which can negatively affect the company’s reputation and financial status due to societal disappointment and environmental harm. In this paper, we aim to comprehensively study this problem through a literature review and an analysis of the behavior against biases of different GNN-based algorithms compared to state-of-the-art methods. We also intend to explore appropriate solutions to tackle this issue with the least possible impact on the model’s performance. © 2023, CC BY.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Context-aware music recommender system based on automatic detection of the user’s physical activity 17th

Context-aware music recommender system based on automatic de...

引用

17th International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2020

作者： Ospina-Bohórquez, Alejandra Gil-González, Ana B. Moreno-García, María N. de Luis-Reboredo, Ana Department of Computer Science and Automation Science Faculty University of Salamanca Plaza de los Caídos. s/n Salamanca37008 Spain

ISBN: (纸本)9783030530358

The large amount of music that can be accessed in streaming nowadays has led to the development of more reliable music recommendation systems. To this end, context-aware music recommendation systems, capable of suggesting music taking into account contextual information, have emerged. Studies have shown that music helps to improve mood while can change the focus of attention of users during the performance of some activity, helping to make this activity more bearable. This work presents a music Context Aware Recommender System in order to motivate users in their daily activities. Its main purpose is to suggest to the user the most appropriate music to improve the performance of the physical activity at recommending time. The conducted experiments along a case study prove that this system is useful and satisfactory when the activity does not require a great deal of concentration. During activities that required movement, most users indicated that the perceived effort decreases when using the recommendation system proposed. They also indicated that their mood had improved after using this system. This demonstrates the usefulness of this recommender system while doing physical activities. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Graph machine learning for flight delay prediction due to holding manouver

arXiv

引用

arXiv 2025年

作者： Franco, Jorge L. Machado Neto, Manoel V. Verri, Filipe A.N. Amancio, Diego R. Institute of Mathematics and Computer Science University of São Paulo São Carlos Brazil Aeronautical Technology Institute – ITA SP São José dos Campos Brazil

Flight delays due to holding maneuvers are a critical and costly phenomenon in aviation, driven by the need to manage air traffic congestion and ensure safety. Holding maneuvers occur when aircraft are instructed to circle in designated airspace, often due to factors such as airport congestion, adverse weather, or air traffic control restrictions. This study models the prediction of flight delays due to holding maneuvers as a graph problem, leveraging advanced Graph Machine Learning (Graph ML) techniques to capture complex interdependencies in air traffic networks. Holding maneuvers, while crucial for safety, cause increased fuel usage, emissions, and passenger dissatisfaction, making accurate prediction essential for operational efficiency. Traditional machine learning models, typically using tabular data, often overlook spatial-temporal relations within air traffic data. To address this, we model the problem of predicting holding as edge feature prediction in a directed (multi)graph where we apply both CatBoost, enriched with graph features capturing network centrality and connectivity, and Graph Attention Networks (GATs), which excel in relational data contexts. Our results indicate that CatBoost outperforms GAT in this imbalanced dataset, effectively predicting holding events and offering interpretability through graph-based feature importance. Additionally, we discuss the model’s potential operational impact through a web-based tool that allows users to simulate real-time delay predictions. This research underscores the viability of graph-based approaches for predictive analysis in aviation, with implications for enhancing fuel efficiency, reducing delays, and improving passenger experience. Copyright © 2025, The Authors. All rights reserved.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：